Spaces:
Running
Running
File size: 73,020 Bytes
6a7f559 025f948 6a7f559 4c6db86 6a7f559 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 |
<!DOCTYPE html>
<html>
<head>
<title>Evaluating Robustness of Reward Models for Mathematical Reasoning</title>
<style>
.hidden {
display: none;
}
</style>
<script src="https://cdn.jsdelivr.net/npm/chart.js"></script>
<script src="https://kit.fontawesome.com/f8ddf9854a.js" crossorigin="anonymous"></script>
<meta charset="utf-8">
<meta name="description"
content="Evaluating Robustness of Reward Models for Mathematical Reasoning">
<meta name="keywords" content="Mathematical Reasoning, Reward Model, Benchmark, RLHF, Reward Hacking, Reward Overoptimization">
<meta name="viewport" content="width=device-width, initial-scale=1">
<title>Evaluating Robustness of Reward Models for Mathematical Reasoning</title>
<link href="https://fonts.googleapis.com/css?family=Google+Sans|Noto+Sans|Castoro" rel="stylesheet">
<link rel="stylesheet" href="./static/css/bulma.min.css">
<link rel="stylesheet" href="./static/css/bulma-carousel.min.css">
<link rel="stylesheet" href="./static/css/bulma-slider.min.css">
<link rel="stylesheet" href="./static/css/fontawesome.all.min.css">
<link rel="stylesheet" href="https://cdn.jsdelivr.net/gh/jpswalsh/academicons@1/css/academicons.min.css">
<link rel="stylesheet" href="./static/css/index.css">
<link rel="stylesheet" href="./static/css/leaderboard.css">
<script type="text/javascript" src="static/js/sort-table.js" defer></script>
<script src="https://ajax.googleapis.com/ajax/libs/jquery/3.5.1/jquery.min.js"></script>
<script defer src="./static/js/fontawesome.all.min.js"></script>
<script src="./static/js/bulma-carousel.min.js"></script>
<script src="./static/js/bulma-slider.min.js"></script>
<script src="./static/js/index.js"></script>
<script src="./static/js/question_card.js"></script>
<script src="./data/results/data_setting.js" defer></script>
<script src="./data/results/model_scores.js" defer></script>
<script src="./visualizer/data/data_public.js" defer></script>
</head>
<!-- Google tag (gtag.js) -->
<script async src="https://www.googletagmanager.com/gtag/js?id=G-PBF77LE136"></script>
<script>
window.dataLayer = window.dataLayer || [];
function gtag(){dataLayer.push(arguments);}
gtag('js', new Date());
gtag('config', 'G-PBF77LE136');
</script>
<body>
<section class="hero">
<div class="hero-body">
<div class="container is-max-desktop">
<div class="columns is-centered">
<div class="column has-text-centered">
<h1 class="title is-1 publication-title is-bold">
<span class="opencodeinterpreter" style="vertical-align: middle">Evaluating Robustness of Reward Models for Mathematical Reasoning</span>
</h1>
<br>
<h3>
Note that this project page is fully anonymized. Some links might not be available due to anonymization.
</h3>
<br>
<!-- <div class="column has-text-centered" style="overflow-x: auto;"> -->
<div class="column has-text-centered">
<div class="publication-links" style="justify-content: center;">
<!-- PDF Link. -->
<span class="link-block">
<!-- @PAN TODO: change links -->
<a href="https://huggingface.co/spaces/RewardMATH/RewardMATH_project/blob/main/ICLR2025_RewardMATH.pdf"
class="external-link button is-normal is-rounded is-dark" target="_blank">
<!-- <span class="icon">
<i class="fas fa-file-pdf"></i>
</span> -->
<span class="icon">
<p style="font-size:18px">📝</p>
</span>
<span>Paper</span>
</a>
</span>
<span class="link-block">
<a href="https://huggingface.co/datasets/RewardMATH/RewardMATH"
class="external-link button is-normal is-rounded is-dark" target="_blank">
<span class="icon">
<p style="font-size:18px">🤗</p>
</span>
<span>Datasets</span>
</a>
</span>
<span class="link-block">
<a href="https://anonymous.4open.science/r/RewardMATH-5BA4/README.md"
class="external-link button is-normal is-rounded is-dark" target="_blank">
<span class="icon">
<i class="fab fa-github"></i>
</span>
<span>Code</span>
</a>
</span>
</div>
</div>
</div>
</div>
</div>
</div>
</section>
<style>
.center {
display: block;
margin-left: auto;
margin-right: auto;
width: 80%;
}
</style>
<section>
<div class="container is-max-desktop">
<!-- Abstract. -->
<div class="columns is-centered has-text-centered">
<div class="column is-four-fifths">
<h2 class="title is-3">Abstract</h2>
<div class="content has-text-justified">
<p>
Reward models are key in reinforcement learning from human feedback (RLHF) systems, aligning the model behavior with human preferences.
Particularly in the math domain, there have been plenty of studies using reward models to align policies for improving reasoning capabilities.
Recently, as the importance of reward models has been emphasized, RewardBench is proposed to understand their behavior.
However, we figure out that the math subset of RewardBench has different representations between chosen and rejected completions, and relies on a single comparison, which may lead to unreliable results as it only see an isolated case.
Therefore, it fails to accurately present the robustness of reward models, leading to a misunderstanding of its performance and potentially resulting in reward hacking.
</p>
<p>
In this work, we introduce a new design for reliable evaluation of reward models, and to validate this, we construct <span class="dnerf">RewardMATH</span>, a benchmark that effectively represents the robustness of reward models in mathematical reasoning tasks.
We demonstrate that the scores on <span class="dnerf">RewardMATH</span> strongly correlate with the results of optimized policy and effectively estimate reward overoptimization, whereas the existing benchmark shows almost no correlation.
The results underscore the potential of our design to enhance the reliability of evaluation, and represent the robustness of reward model.
</p>
<p>
</p>
</div>
</div>
</div>
<!--/ Abstract. -->
</div>
</section>
<section class="hero is-light is-small">
<div class="hero-body has-text-centered">
<h1 class="title is-1 mmmu">
<span class="mmmu" style="vertical-align: middle">Preliminaries</span>
</h1>
</div>
</section>
<section class="section">
<div class="container">
<div class="columns is-centered has-text-centered">
<!-- <div class="column is-full-width has-text-centered"> -->
<div class="column is-four-fifths">
<h2 class="title is-3">Robustness of reward model</h2>
<div class="content has-text-justified">
<p>
<i>Reward hacking</i> represents a significant challenge in the development and implementation of reward models for RLHF.
This phenomenon occurs when policies exploit loopholes in reward models to achieve higher scores, stemming from discrepancies between human preferences (the true reward function) and proxy reward models.
Such issues underscore the importance of evaluating reward models themselves, not just policy models (post-RLHF models).
The reward hacking can lead to <b>reward overoptimization</b>, where employing a proxy reward model for optimization may initially improve the true reward but gradually leads to degradation, ultimately resulting in optimization failure.
</p>
<p>
In this work, we argue that the <i>robustness of a reward model should be evaluated based on how effectively it provides signals from which a policy can learn.</i>
</p>
</div>
</div>
</div>
</div>
</section>
<section class="hero is-light is-small">
<div class="hero-body has-text-centered">
<h1 class="title is-1 mmmu">
<span class="mmmu" style="vertical-align: middle">Designing a Reliable Benchmark</span>
</h1>
</div>
</section>
<section class="section">
<div class="container">
<div class="columns is-centered has-text-centered">
<!-- <div class="column is-full-width has-text-centered"> -->
<div class="column is-four-fifths">
<h2 class="title is-3">On the road to the Evaluation of Robustness of Reward Model</h2>
<div class="content has-text-centered">
<img src="static/images/motivation.png" alt="Motivation" class="center" style="width:80%">
<p> A motivation example from math subset of RewardBench and drawbacks of the existing evaluation method.</p>
</div>
<div class="content has-text-justified">
<p>
RewardBench, a widely-used benchmark for reward models, does not fully address the robustness of models in the math domain, with recent findings showing about 20% of the annotations in its underlying PRM800K dataset are incorrect.
The evaluation process in RewardBench, which compares rewards between chosen and rejected solutions annotated by unaligned GPT-4, is flawed due to humans often skipping steps in solutions, leading to discrepancies with machine-generated solutions.
These discrepancies challenge the evaluation’s reliability, as comparing with a single incorrect solution does not sufficiently assess the robustness of reward models.
</p>
</div>
<br/>
<h2 class="title is-3">RewardMATH</h2>
<div class="content has-text-centered">
<img src="static/images/RewardMATH.png" alt="statstics of RewardMATH" class="center" style="width:90%">
<p> A histogram showing the distribution of samples by the number of steps on RewardBench and <span class="dnerf">RewardMATH</span>, and the contribution of each model to the rejected solutions.</p>
</div>
<div class="content has-text-justified">
<p>
The design philosophy of <span class="dnerf">RewardMATH</span> is to caution against a hasty generalization, which occurs when conclusions are drawn from a sample that is too small or consists of too few cases.
To design a reliable benchmark, we aim to mitigate the risk of reward hacking and employs comparisons with a variety of incorrect (i.e., rejected) solutions.
Therefore, we introduce <span class="dnerf">RewardMATH</span>, a reliable benchmark crafted for evaluating the robustness of reward models in mathematical reasoning.
</p>
</div>
<br/>
<h2 class="title is-3">Evaluation metric</h2>
<div class="content has-text-justified">
<p>
For each problem, we infer 10 solutions in total<span>—</span>1 correct solution and 9 incorrect solutions<span>—</span>and then assign a true classification label when a reward of chosen solution is higher than all rewards of rejected solutions.
Furthermore, considering only whether the reward of chosen solution is the highest can be fairly strict, we also utilize Mean Reciprocal Rank (MRR), where higher ranks for the chosen solution lead to higher scores.
</p>
</div>
</div>
</div>
</div>
</div>
</section>
<section class="hero is-light is-small">
<div class="hero-body has-text-centered">
<h1 class="title is-1 mmmu">
<span class="mmmu" style="vertical-align: middle">Evaluating Reward Models</span>
</h1>
</div>
</section>
<section class="section">
<div class="container">
<div class="columns is-centered has-text-centered" style="flex-direction: column; align-items: center;">
<!-- <div class="column is-full-width has-text-centered"> -->
<div class="column is-four-fifths">
<br/>
<div class="content has-text-centered">
<img src="static/images/main_results_1.png" alt="Results of generative RMs" width="60%"/>
<p>
The results of generative reward models on RewardBench and <span class="dnerf">RewardMATH</span>.
</p>
</div>
<div class="content has-text-justified">
<p>
The results from RewardBench suggest that LLMs, such as GPT-4 or Prometheus-2-7B, could potentially serve as effective reward models.
However, more thorough evaluations on <span class="dnerf">RewardMATH</span> indicate that LLMs generally do not perform well as reward models, with most achieving scores close to zero, except for those in the GPT-4 family.
Through direct assessment that considers the presence of ties, we find that most LLMs fail to distinguish between correct and incorrect solutions, simply assigning the same scores to all.
</p>
</div>
</div>
<div class="column is-four-fifths">
<br/>
<div class="content has-text-centered">
<img src="static/images/main_results_2.png" alt="Results of classifier-based RMs and PRMs" width="40%"/>
<p>
The results of classifier-based RMs and PRMs on RewardBench and <span class="dnerf">RewardMATH</span>.
</p>
</div>
<div class="content has-text-justified">
<p>
Rankings on RewardBench do not consistently predict performance on <span class="dnerf">RewardMATH</span>.
Specifically, Oasst-rm-2.1-pythia-1.4b, which is one of the top-ranked models in RewardBench, faces challenges in <span class="dnerf">RewardMATH</span>, scoring lower than Beavor-7b-v2.0-reward, the lowest-ranked model in RewardBench.
However, Internlm2-7b-reward exhibits the highest performance in <span class="dnerf">RewardMATH</span>, suggesting that it is genuinely a robust reward model for mathematical reasoning.
</p>
</div>
</div>
</div>
</div>
</section>
<!-- RESULTS SECTION -->
<section class="hero is-light is-small">
<div class="hero-body has-text-centered">
<h1 class="title is-1 mmmu">
<span class="mmmu" style="vertical-align: middle">Validating Our Design for a Reliable Benchmark</span>
</h1>
</div>
</section>
<section class="section">
<div class="container">
<div class="columns is-centered has-text-centered" style="flex-direction: column; align-items: center;">
<!-- <div class="column is-full-width has-text-centered"> -->
<div class="column is-four-fifths">
<h2 class="title is-3">Reliability of Benchmark</h2>
<div class="content has-text-centered">
<img src="static/images/correlation.svg" alt="Results of generative RMs" width="80%"/>
<p>
The relationship between the difference in accuracy on math test sets and the performance based on the benchmark design.
</p>
</div>
<br/>
<div class="content has-text-justified">
<p>
<span class="dnerf">RewardMATH</span> shows a strong positive correlation between the benchmark scores and the results of optimized policy, indicating its reliability, whereas RewardBench shows only a weak correlation.
Additionally, the analysis explores the design of evaluation sets that prevent reward hacking by comparing chosen and rejected solutions from the two benchmarks.
The results of heatmap highlight that the importance of minimizing the representation differences between chosen and rejected solutions to mitigate vulnerability to reward hacking, as well as employing one-to-many comparisons for more reliable evaluations.
</p>
</div>
</div>
<div class="column is-four-fifths">
<h2 class="title is-3">Through the Lens of Reward Overoptimization</h2>
<div class="content has-text-centered">
<img src="static/images/data_size_reward.png" alt="Reward overoptimization" width="100%"/>
<p>
Gold rewards and oracle rewards (pass@1) in BoN and PPO experiments with proxy reward models across different amounts of data in a synthetic setup.
</p>
</div>
<br/>
<div class="content has-text-justified">
<p>
Typically, a robust proxy reward model trained to capture human preferences should exhibit increasing gold rewards as KL divergence increases.
Conversely, a collapse in gold rewards at certain point during an increase in KL divergence indicates a lack of robustness in the proxy reward model.
Figure illustrates how dataset size impacts the behavior of reward model within a synthetic setup.
We find that proxy reward models trained on smaller datasets reach peak rewards at lower KL divergences, indicating faster overoptimization.
This finding suggests that larger datasets can help mitigate reward overoptimization.
Furthermore, we confirm that reward overoptimization can also be observed through oracle rewards (i.e., pass@1) in tasks with well-defined human preferences, such as mathematics.
</p>
</div>
<br/>
<div class="content has-text-centered">
<img src="static/images/reward_overoptimization.svg" alt="Results of classifier-based RMs and PRMs" width="70%"/>
<p>
Gold and oracle rewards (pass@1) for BoN experiments with MetaMATH-Mistral-7B.
</p>
</div>
<br/>
<div class="content has-text-justified">
<p>
Figure shows gold and oracle rewards change with increasing KL divergence and reveals varying effects of overoptimization across different models.
Notably, high-performing models on RewardBench, like Oasst-rm-2.1-pythia-1.4b, often exhibit rapid overoptimization without a consistent correlation between benchmark performance and the extent of overoptimization.
In contrast, <span class="dnerf">RewardMATH</span> demonstrates a clear trend where higher performance correlates with less reward collapse, highlighting its reliability in providing accurate rewards and effectively mitigating overoptimization.
</p>
</div>
</div>
<!-- <br/>
<div class="content has-text-centered"></div>
<img src="static/images/reward_overoptimization.svg" alt="Results of classifier-based RMs and PRMs" width="70%"/>
<p>
Gold and oracle rewards (pass@1) for BoN experiments with MetaMATH-Mistral-7B.
</p>
</div>
<div class="content has-text-justified">
<p>
Figure shows gold and oracle rewards change with increasing KL divergence and reveals varying effects of overoptimization across different models.
Notably, high-performing models on RewardBench, like Oasst-rm-2.1-pythia-1.4b, often exhibit rapid overoptimization without a consistent correlation between benchmark performance and the extent of overoptimization.
In contrast, <span class="dnerf">RewardMATH</span> demonstrates a clear trend where higher performance correlates with less reward collapse, highlighting its reliability in providing accurate rewards and effectively mitigating overoptimization.
</p>
</div>
<br/>
</div> -->
</div>
</div>
</section>
<section class="hero is-light is-small">
<div class="hero-body has-text-centered">
<h1 class="title is-1 mmmu">
<span class="mmmu" style="vertical-align: middle">Discussion</span>
</h1>
</div>
</section>
<section class="section">
<div class="container">
<div class="columns is-centered has-text-centered">
<!-- <div class="column is-full-width has-text-centered"> -->
<div class="column is-four-fifths">
<h2 class="title is-3">Developing effective RLHF systems</h2>
<div class="content has-text-justified">
<p>
Benchmarks serve as critical milestones in advancing artificial intelligence.
In this work, we argue that a benchmark for reward models should reliably assess their robustness, where a robust RM indicates
a model that provide useful signals to enable effective policy learning.
Through extensive experiments, we confirm that our reliable benchmark design, which mitigates the risk of reward hacking and employs one-to-many comparisons, accurately reflects the robustness of reward models.
While this work marks a significant step forward, there is still room for improvement.
We validate our design in mathematical reasoning tasks, where human preferences can be clearly defined by correctness, making it easier to gather multiple rejected completions.
Since the reward models can be applied to a wide range of tasks, a crucial next step is to extend our design to cover all of them.
We hope that advancing this line of research will provide a promising path toward developing more trustworthy and effective RLHF systems.
</p>
</div>
<h2 class="title is-3">Conclusion</h2>
<div class="content has-text-justified">
<p>
In this work, we suggest a new design for reliable evaluation of reward models: (1) mitigating the risk of reward hacking and (2) employing a one-to-many comparison.
To validate our design, we propose <span class="dnerf">RewardMATH</span>, a benchmark that effectively represents the robustness of reward models in mathematical reasoning tasks.
Our extensive experiments demonstrate that the performance on <span class="dnerf">RewardMATH</span> has a strong correlation with the performance of the optimized policy, whereas the existing benchmark shows no correlation.
Furthermore, we also confirm that <span class="dnerf">RewardMATH</span> can effectively estimate the reward overoptimization, a critical concern in RLHF systems.
</p>
</div>
</div>
</div>
</div>
</div>
</section>
<!-- @PAN TODO: bibtex -->
<section class="section" id="BibTeX">
<div class="container is-max-desktop content">
<h2 class="title is-3 has-text-centered">BibTeX</h2>
<pre><code>
@article{Anonymized,
title={Evaluating Robustness of Reward Models for Mathematical Reasoning},
author={Anonymized},
journal={Anonymized},
year={2024}
}
</code></pre>
</div>
</section>
<footer class="footer">
<!-- <div class="container"> -->
<div class="content has-text-centered">
</div>
<div class="columns is-centered">
<div class="column is-8">
<div class="content">
<p>
This website is website adapted from <a href="https://nerfies.github.io/">Nerfies</a> and <a href="https://mmmu.github.io/">MMMU</a>, licensed under a <a rel="license"
href="http://creativecommons.org/licenses/by-sa/4.0/">Creative
Commons Attribution-ShareAlike 4.0 International License</a>.
</p>
</div>
</div>
</div>
<!-- </div> -->
</footer>
<script>
function sortTable(table, column, type, asc) {
var tbody = table.tBodies[0];
var rows = Array.from(tbody.rows);
rows.sort(function(a, b) {
var valA = a.cells[column].textContent;
var valB = b.cells[column].textContent;
if (type === 'number') {
valA = parseFloat(valA);
valB = parseFloat(valB);
}
return asc ? valA - valB : valB - valA;
});
rows.forEach(row => tbody.appendChild(row));
}
// 切换表格的函数
function toggleTables () {
var table1 = document.getElementById('table1');
var table2 = document.getElementById('table2');
table1.classList.toggle('hidden');
table2.classList.toggle('hidden');
}
document.getElementById('toggleButton').addEventListener('click', toggleTables);
const canvas = document.getElementById('difficulty_level_chart');
canvas.style.width = '500px';
canvas.style.height = '120px';
const ctx = document.getElementById('difficulty_level_chart').getContext('2d');
const difficulty_level_chart = new Chart(ctx, {
type: 'bar',
data: {
labels: ['Easy', 'Medium', 'Hard', 'Overall'],
datasets: [{
label: 'Fuyu-8B',
data: [28.9, 27, 26.4, 27.4],
backgroundColor: 'rgba(196, 123, 160, 0.6)',
borderColor: 'rgba(196, 123, 160, 1)',
borderWidth: 1,
hoverBackgroundColor: 'rgba(196, 123, 160, 1)'
},
{
label: 'Qwen-VL-7B',
data: [39.4, 31.9, 27.6, 32.9],
backgroundColor: 'rgba(245, 123, 113, 0.6)',
borderColor: 'rgba(245, 123, 113, 1)',
borderWidth: 1,
hoverBackgroundColor: 'rgba(245, 123, 113, 1)'
},
{
label: 'LLaVA-1.5-13B',
data: [41.3, 32.7, 26.7, 33.6],
backgroundColor: 'rgba(255, 208, 80, 0.6)',
borderColor: 'rgba(255, 208, 80, 1)',
borderWidth: 1,
hoverBackgroundColor: 'rgba(255, 208, 80, 1)'
},
{
label: 'InstructBLIP-T5-XXL',
data: [40.3, 32.3, 29.4, 33.8],
backgroundColor: 'rgba(110, 194, 134, 0.6)',
borderColor: 'rgba(110, 194, 134, 1)',
borderWidth: 1,
hoverBackgroundColor: 'rgba(110, 194, 134, 1)'
},
{
label: 'BLIP-2 FLAN-T5-XXL',
data: [41, 32.7, 28.5, 34],
backgroundColor: 'rgba(255, 153, 78, 0.6)',
borderColor: 'rgba(255, 153, 78, 1)',
borderWidth: 1,
hoverBackgroundColor: 'rgba(255, 153, 78, 1)'
},
{
label: 'GPT-4V',
data: [76.1, 55.6, 31.2, 55.7],
backgroundColor: 'rgba(117, 209, 215, 0.6)',
borderColor: 'rgba(117, 209, 215, 1)',
borderWidth: 1,
hoverBackgroundColor: 'rgba(117, 209, 215, 1)'
}]
},
options: {
scales: {
y: {
beginAtZero: true,
min: 0,
max: 100,
ticks: {
stepSize: 20,
font: {
size: 16
}
}
},
x: {
ticks: {
font: {
size: 16 // 设置X轴字体大小
}
}
}
},
plugins: {
legend: {
labels: {
font: {
size: 16 // 设置标签文字大小
}
}
},
tooltip: {
callbacks: {
label: function(context) {
return context.dataset.label + ': ' + context.parsed.y;
}
}
}
},
onHover: (event, chartElement) => {
event.native.target.style.cursor = chartElement[0] ? 'pointer' : 'default';
}
}
});
document.addEventListener('DOMContentLoaded', function() {
// Data for the "Diagrams" chart
const data_Diagrams = {
labels: ['Fuyu-8B', 'Qwen-VL-7B', 'InstructBLIP-T5-XXL', 'LLaVA-1.5-13B', 'BLIP-2 FLAN-T5-XXL', 'GPT-4V'],
datasets: [{
data: [27.6, 30.1, 31.8, 30.0, 32.0, 46.8],
backgroundColor: ['rgba(196, 123, 160, 0.6)', 'rgba(245, 123, 113, 0.6)', 'rgba(255, 208, 80, 0.6)', 'rgba(110, 194, 134, 0.6)', 'rgba(255, 153, 78, 0.6)', 'rgba(117, 209, 215, 0.6)'],
borderColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,0.4)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)'],
hoverBackgroundColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,1)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)']
}]
};
// "data_Diagrams" chart
new Chart(document.getElementById('chart_Diagrams'), {
type: 'bar',
data: data_Diagrams,
options: {
scales: {
y: {
beginAtZero: true,
min: 0,
max: 100,
ticks: {
stepSize: 20
}
},
x: {
display: false
}
},
plugins: {
legend: {
display: false
},
tooltip: {
}
}
}
});
// "data_Tables" chart
const data_Tables = {
labels: ['Fuyu-8B', 'Qwen-VL-7B', 'InstructBLIP-T5-XXL', 'LLaVA-1.5-13B', 'BLIP-2 FLAN-T5-XXL', 'GPT-4V'],
datasets: [{
data: [26.6, 29.0, 29.8, 27.8, 27.8, 61.8],
backgroundColor: ['rgba(196, 123, 160, 0.6)', 'rgba(245, 123, 113, 0.6)', 'rgba(255, 208, 80, 0.6)', 'rgba(110, 194, 134, 0.6)', 'rgba(255, 153, 78, 0.6)', 'rgba(117, 209, 215, 0.6)'],
borderColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,0.4)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)'],
hoverBackgroundColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,1)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)']
}]
};
new Chart(document.getElementById('chart_Tables'), {
type: 'bar',
data: data_Tables,
options: {
scales: {
y: {
beginAtZero: true,
min: 0,
max: 100,
ticks: {
stepSize: 20
}
},
x: {
display: false
}
},
plugins: {
legend: {
display: false
},
tooltip: {
}
}
}
});
// "data_PlotsAndCharts " chart
const data_PlotsAndCharts = {
labels: ['Fuyu-8B', 'Qwen-VL-7B', 'InstructBLIP-T5-XXL', 'LLaVA-1.5-13B', 'BLIP-2 FLAN-T5-XXL', 'GPT-4V'],
datasets: [{
data: [24.8, 31.8, 36.2, 30.4, 35.8, 55.6],
backgroundColor: ['rgba(196, 123, 160, 0.6)', 'rgba(245, 123, 113, 0.6)', 'rgba(255, 208, 80, 0.6)', 'rgba(110, 194, 134, 0.6)', 'rgba(255, 153, 78, 0.6)', 'rgba(117, 209, 215, 0.6)'],
borderColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,0.4)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)'],
hoverBackgroundColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,1)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)']
}]
};
new Chart(document.getElementById('chart_PlotsAndCharts'), {
type: 'bar',
data: data_PlotsAndCharts ,
options: {
scales: {
y: {
beginAtZero: true,
min: 0,
max: 100,
ticks: {
stepSize: 20
}
},
x: {
display: false
}
},
plugins: {
legend: {
display: false
},
tooltip: {
}
}
}
});
// "data_ChemicalStructures " chart
const data_ChemicalStructures = {
labels: ['Fuyu-8B', 'Qwen-VL-7B', 'InstructBLIP-T5-XXL', 'LLaVA-1.5-13B', 'BLIP-2 FLAN-T5-XXL', 'GPT-4V'],
datasets: [{
data: [25.0, 27.2, 27.1, 26.7, 25.5, 50.6],
backgroundColor: ['rgba(196, 123, 160, 0.6)', 'rgba(245, 123, 113, 0.6)', 'rgba(255, 208, 80, 0.6)', 'rgba(110, 194, 134, 0.6)', 'rgba(255, 153, 78, 0.6)', 'rgba(117, 209, 215, 0.6)'],
borderColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,0.4)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)'],
hoverBackgroundColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,1)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)']
}]
};
new Chart(document.getElementById('chart_ChemicalStructures'), {
type: 'bar',
data: data_ChemicalStructures ,
options: {
scales: {
y: {
beginAtZero: true,
min: 0,
max: 100,
ticks: {
stepSize: 20
}
},
x: {
display: false
}
},
plugins: {
legend: {
display: false
},
tooltip: {
}
}
}
});
// "data_Photographs " chart
const data_Photographs = {
labels: ['Fuyu-8B', 'Qwen-VL-7B', 'InstructBLIP-T5-XXL', 'LLaVA-1.5-13B', 'BLIP-2 FLAN-T5-XXL', 'GPT-4V'],
datasets: [{
data: [27.6, 40.5, 41.4, 44.4, 42.0, 64.2],
backgroundColor: ['rgba(196, 123, 160, 0.6)', 'rgba(245, 123, 113, 0.6)', 'rgba(255, 208, 80, 0.6)', 'rgba(110, 194, 134, 0.6)', 'rgba(255, 153, 78, 0.6)', 'rgba(117, 209, 215, 0.6)'],
borderColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,0.4)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)'],
hoverBackgroundColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,1)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)']
}]
};
new Chart(document.getElementById('chart_Photographs'), {
type: 'bar',
data: data_Photographs ,
options: {
scales: {
y: {
beginAtZero: true,
min: 0,
max: 100,
ticks: {
stepSize: 20
}
},
x: {
display: false
}
},
plugins: {
legend: {
display: false
},
tooltip: {
}
}
}
});
// "data_Paintings " chart
const data_Paintings = {
labels: ['Fuyu-8B', 'Qwen-VL-7B', 'InstructBLIP-T5-XXL', 'LLaVA-1.5-13B', 'BLIP-2 FLAN-T5-XXL', 'GPT-4V'],
datasets: [{
data: [28.7, 57.2, 53.6, 56.3, 52.1, 75.9],
backgroundColor: ['rgba(196, 123, 160, 0.6)', 'rgba(245, 123, 113, 0.6)', 'rgba(255, 208, 80, 0.6)', 'rgba(110, 194, 134, 0.6)', 'rgba(255, 153, 78, 0.6)', 'rgba(117, 209, 215, 0.6)'],
borderColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,0.4)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)'],
hoverBackgroundColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,1)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)']
}]
};
new Chart(document.getElementById('chart_Paintings'), {
type: 'bar',
data: data_Paintings ,
options: {
scales: {
y: {
beginAtZero: true,
min: 0,
max: 100,
ticks: {
stepSize: 20
}
},
x: {
display: false
}
},
plugins: {
legend: {
display: false
},
tooltip: {
}
}
}
});
// "data_GeometricShapes " chart
const data_GeometricShapes = {
labels: ['Fuyu-8B', 'Qwen-VL-7B', 'InstructBLIP-T5-XXL', 'LLaVA-1.5-13B', 'BLIP-2 FLAN-T5-XXL', 'GPT-4V'],
datasets: [{
data: [21.1, 25.3, 21.4, 25.6, 28.3, 40.2],
backgroundColor: ['rgba(196, 123, 160, 0.6)', 'rgba(245, 123, 113, 0.6)', 'rgba(255, 208, 80, 0.6)', 'rgba(110, 194, 134, 0.6)', 'rgba(255, 153, 78, 0.6)', 'rgba(117, 209, 215, 0.6)'],
borderColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,0.4)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)'],
hoverBackgroundColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,1)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)']
}]
};
new Chart(document.getElementById('chart_GeometricShapes'), {
type: 'bar',
data: data_GeometricShapes ,
options: {
scales: {
y: {
beginAtZero: true,
min: 0,
max: 100,
ticks: {
stepSize: 20
}
},
x: {
display: false
}
},
plugins: {
legend: {
display: false
},
tooltip: {
}
}
}
});
// "data_SheetMusic " chart
const data_SheetMusic = {
labels: ['Fuyu-8B', 'Qwen-VL-7B', 'InstructBLIP-T5-XXL', 'LLaVA-1.5-13B', 'BLIP-2 FLAN-T5-XXL', 'GPT-4V'],
datasets: [{
data: [35.2, 33.4, 34.6, 35.8, 34.9, 38.8],
backgroundColor: ['rgba(196, 123, 160, 0.6)', 'rgba(245, 123, 113, 0.6)', 'rgba(255, 208, 80, 0.6)', 'rgba(110, 194, 134, 0.6)', 'rgba(255, 153, 78, 0.6)', 'rgba(117, 209, 215, 0.6)'],
borderColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,0.4)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)'],
hoverBackgroundColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,1)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)']
}]
};
new Chart(document.getElementById('chart_SheetMusic'), {
type: 'bar',
data: data_SheetMusic ,
options: {
scales: {
y: {
beginAtZero: true,
min: 0,
max: 100,
ticks: {
stepSize: 20
}
},
x: {
display: false
}
},
plugins: {
legend: {
display: false
},
tooltip: {
}
}
}
});
// "data_MedicalImages " chart
const data_MedicalImages = {
labels: ['Fuyu-8B', 'Qwen-VL-7B', 'InstructBLIP-T5-XXL', 'LLaVA-1.5-13B', 'BLIP-2 FLAN-T5-XXL', 'GPT-4V'],
datasets: [{
data: [25.4, 29.8, 31.6, 36.4, 29.8, 59.6],
backgroundColor: ['rgba(196, 123, 160, 0.6)', 'rgba(245, 123, 113, 0.6)', 'rgba(255, 208, 80, 0.6)', 'rgba(110, 194, 134, 0.6)', 'rgba(255, 153, 78, 0.6)', 'rgba(117, 209, 215, 0.6)'],
borderColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,0.4)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)'],
hoverBackgroundColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,1)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)']
}]
};
new Chart(document.getElementById('chart_MedicalImages'), {
type: 'bar',
data: data_MedicalImages ,
options: {
scales: {
y: {
beginAtZero: true,
min: 0,
max: 100,
ticks: {
stepSize: 20
}
},
x: {
display: false
}
},
plugins: {
legend: {
display: false
},
tooltip: {
}
}
}
});
// "data_PathologicalImages " chart
const data_PathologicalImages = {
labels: ['Fuyu-8B', 'Qwen-VL-7B', 'InstructBLIP-T5-XXL', 'LLaVA-1.5-13B', 'BLIP-2 FLAN-T5-XXL', 'GPT-4V'],
datasets: [{
data: [26.5, 27.7, 31.2, 35.2, 35.6, 63.6],
backgroundColor: ['rgba(196, 123, 160, 0.6)', 'rgba(245, 123, 113, 0.6)', 'rgba(255, 208, 80, 0.6)', 'rgba(110, 194, 134, 0.6)', 'rgba(255, 153, 78, 0.6)', 'rgba(117, 209, 215, 0.6)'],
borderColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,0.4)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)'],
hoverBackgroundColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,1)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)']
}]
};
new Chart(document.getElementById('chart_PathologicalImages'), {
type: 'bar',
data: data_PathologicalImages ,
options: {
scales: {
y: {
beginAtZero: true,
min: 0,
max: 100,
ticks: {
stepSize: 20
}
},
x: {
display: false
}
},
plugins: {
legend: {
display: false
},
tooltip: {
}
}
}
});
// "data_MicroscopicImages " chart
const data_MicroscopicImages = {
labels: ['Fuyu-8B', 'Qwen-VL-7B', 'InstructBLIP-T5-XXL', 'LLaVA-1.5-13B', 'BLIP-2 FLAN-T5-XXL', 'GPT-4V'],
datasets: [{
data: [27.0, 37.6, 29.2, 36.3, 32.7, 58.0],
backgroundColor: ['rgba(196, 123, 160, 0.6)', 'rgba(245, 123, 113, 0.6)', 'rgba(255, 208, 80, 0.6)', 'rgba(110, 194, 134, 0.6)', 'rgba(255, 153, 78, 0.6)', 'rgba(117, 209, 215, 0.6)'],
borderColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,0.4)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)'],
hoverBackgroundColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,1)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)']
}]
};
new Chart(document.getElementById('chart_MicroscopicImages'), {
type: 'bar',
data: data_MicroscopicImages ,
options: {
scales: {
y: {
beginAtZero: true,
min: 0,
max: 100,
ticks: {
stepSize: 20
}
},
x: {
display: false
}
},
plugins: {
legend: {
display: false
},
tooltip: {
}
}
}
});
// "data_MRIsCTScansXrays " chart
const data_MRIsCTScansXrays = {
labels: ['Fuyu-8B', 'Qwen-VL-7B', 'InstructBLIP-T5-XXL', 'LLaVA-1.5-13B', 'BLIP-2 FLAN-T5-XXL', 'GPT-4V'],
datasets: [{
data: [21.7, 36.9, 33.3, 39.4, 29.8, 50.0],
backgroundColor: ['rgba(196, 123, 160, 0.6)', 'rgba(245, 123, 113, 0.6)', 'rgba(255, 208, 80, 0.6)', 'rgba(110, 194, 134, 0.6)', 'rgba(255, 153, 78, 0.6)', 'rgba(117, 209, 215, 0.6)'],
borderColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,0.4)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)'],
hoverBackgroundColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,1)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)']
}]
};
new Chart(document.getElementById('chart_MRIsCTScansXrays'), {
type: 'bar',
data: data_MRIsCTScansXrays ,
options: {
scales: {
y: {
beginAtZero: true,
min: 0,
max: 100,
ticks: {
stepSize: 20
}
},
x: {
display: false
}
},
plugins: {
legend: {
display: false
},
tooltip: {
}
}
}
});
// "data_SketchesAndDrafts " chart
const data_SketchesAndDrafts = {
labels: ['Fuyu-8B', 'Qwen-VL-7B', 'InstructBLIP-T5-XXL', 'LLaVA-1.5-13B', 'BLIP-2 FLAN-T5-XXL', 'GPT-4V'],
datasets: [{
data: [37.0, 32.1, 29.9, 38.0, 33.7, 55.4],
backgroundColor: ['rgba(196, 123, 160, 0.6)', 'rgba(245, 123, 113, 0.6)', 'rgba(255, 208, 80, 0.6)', 'rgba(110, 194, 134, 0.6)', 'rgba(255, 153, 78, 0.6)', 'rgba(117, 209, 215, 0.6)'],
borderColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,0.4)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)'],
hoverBackgroundColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,1)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)']
}]
};
new Chart(document.getElementById('chart_SketchesAndDrafts'), {
type: 'bar',
data: data_SketchesAndDrafts ,
options: {
scales: {
y: {
beginAtZero: true,
min: 0,
max: 100,
ticks: {
stepSize: 20
}
},
x: {
display: false
}
},
plugins: {
legend: {
display: false
},
tooltip: {
}
}
}
});
// "data_Maps " chart
const data_Maps = {
labels: ['Fuyu-8B', 'Qwen-VL-7B', 'InstructBLIP-T5-XXL', 'LLaVA-1.5-13B', 'BLIP-2 FLAN-T5-XXL', 'GPT-4V'],
datasets: [{
data: [38.2, 36.5, 45.9, 47.6, 43.5, 61.8],
backgroundColor: ['rgba(196, 123, 160, 0.6)', 'rgba(245, 123, 113, 0.6)', 'rgba(255, 208, 80, 0.6)', 'rgba(110, 194, 134, 0.6)', 'rgba(255, 153, 78, 0.6)', 'rgba(117, 209, 215, 0.6)'],
borderColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,0.4)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)'],
hoverBackgroundColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,1)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)']
}]
};
new Chart(document.getElementById('chart_Maps'), {
type: 'bar',
data: data_Maps ,
options: {
scales: {
y: {
beginAtZero: true,
min: 0,
max: 100,
ticks: {
stepSize: 20
}
},
x: {
display: false
}
},
plugins: {
legend: {
display: false
},
tooltip: {
}
}
}
});
// "data_TechnicalBlueprints " chart
const data_TechnicalBlueprints = {
labels: ['Fuyu-8B', 'Qwen-VL-7B', 'InstructBLIP-T5-XXL', 'LLaVA-1.5-13B', 'BLIP-2 FLAN-T5-XXL', 'GPT-4V'],
datasets: [{
data: [24.7, 25.9, 28.4, 25.3, 27.8, 38.9],
backgroundColor: ['rgba(196, 123, 160, 0.6)', 'rgba(245, 123, 113, 0.6)', 'rgba(255, 208, 80, 0.6)', 'rgba(110, 194, 134, 0.6)', 'rgba(255, 153, 78, 0.6)', 'rgba(117, 209, 215, 0.6)'],
borderColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,0.4)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)'],
hoverBackgroundColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,1)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)']
}]
};
new Chart(document.getElementById('chart_TechnicalBlueprints'), {
type: 'bar',
data: data_TechnicalBlueprints ,
options: {
scales: {
y: {
beginAtZero: true,
min: 0,
max: 100,
ticks: {
stepSize: 20
}
},
x: {
display: false
}
},
plugins: {
legend: {
display: false
},
tooltip: {
}
}
}
});
// "data_TreesAndGraphs " chart
const data_TreesAndGraphs = {
labels: ['Fuyu-8B', 'Qwen-VL-7B', 'InstructBLIP-T5-XXL', 'LLaVA-1.5-13B', 'BLIP-2 FLAN-T5-XXL', 'GPT-4V'],
datasets: [{
data: [30.1, 28.1, 28.8, 28.8, 34.9, 50.0],
backgroundColor: ['rgba(196, 123, 160, 0.6)', 'rgba(245, 123, 113, 0.6)', 'rgba(255, 208, 80, 0.6)', 'rgba(110, 194, 134, 0.6)', 'rgba(255, 153, 78, 0.6)', 'rgba(117, 209, 215, 0.6)'],
borderColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,0.4)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)'],
hoverBackgroundColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,1)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)']
}]
};
new Chart(document.getElementById('chart_TreesAndGraphs'), {
type: 'bar',
data: data_TreesAndGraphs ,
options: {
scales: {
y: {
beginAtZero: true,
min: 0,
max: 100,
ticks: {
stepSize: 20
}
},
x: {
display: false
}
},
plugins: {
legend: {
display: false
},
tooltip: {
}
}
}
});
// "data_MathematicalNotations " chart
const data_MathematicalNotations = {
labels: ['Fuyu-8B', 'Qwen-VL-7B', 'InstructBLIP-T5-XXL', 'LLaVA-1.5-13B', 'BLIP-2 FLAN-T5-XXL', 'GPT-4V'],
datasets: [{
data: [15.8, 27.1, 22.6, 21.8, 21.1, 45.9],
backgroundColor: ['rgba(196, 123, 160, 0.6)', 'rgba(245, 123, 113, 0.6)', 'rgba(255, 208, 80, 0.6)', 'rgba(110, 194, 134, 0.6)', 'rgba(255, 153, 78, 0.6)', 'rgba(117, 209, 215, 0.6)'],
borderColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,0.4)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)'],
hoverBackgroundColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,1)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)']
}]
};
new Chart(document.getElementById('chart_MathematicalNotations'), {
type: 'bar',
data: data_MathematicalNotations ,
options: {
scales: {
y: {
beginAtZero: true,
min: 0,
max: 100,
ticks: {
stepSize: 20
}
},
x: {
display: false
}
},
plugins: {
legend: {
display: false
},
tooltip: {
}
}
}
});
// "data_ComicsAndCartoons " chart
const data_ComicsAndCartoons = {
labels: ['Fuyu-8B', 'Qwen-VL-7B', 'InstructBLIP-T5-XXL', 'LLaVA-1.5-13B', 'BLIP-2 FLAN-T5-XXL', 'GPT-4V'],
datasets: [{
data: [29.0, 51.9, 49.6, 54.2, 51.1, 68.7],
backgroundColor: ['rgba(196, 123, 160, 0.6)', 'rgba(245, 123, 113, 0.6)', 'rgba(255, 208, 80, 0.6)', 'rgba(110, 194, 134, 0.6)', 'rgba(255, 153, 78, 0.6)', 'rgba(117, 209, 215, 0.6)'],
borderColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,0.4)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)'],
hoverBackgroundColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,1)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)']
}]
};
new Chart(document.getElementById('chart_ComicsAndCartoons'), {
type: 'bar',
data: data_ComicsAndCartoons ,
options: {
scales: {
y: {
beginAtZero: true,
min: 0,
max: 100,
ticks: {
stepSize: 20
}
},
x: {
display: false
}
},
plugins: {
legend: {
display: false
},
tooltip: {
}
}
}
});
// "data_Sculpture " chart
const data_Sculpture = {
labels: ['Fuyu-8B', 'Qwen-VL-7B', 'InstructBLIP-T5-XXL', 'LLaVA-1.5-13B', 'BLIP-2 FLAN-T5-XXL', 'GPT-4V'],
datasets: [{
data: [30.8, 46.2, 49.6, 51.3, 53.0, 76.1],
backgroundColor: ['rgba(196, 123, 160, 0.6)', 'rgba(245, 123, 113, 0.6)', 'rgba(255, 208, 80, 0.6)', 'rgba(110, 194, 134, 0.6)', 'rgba(255, 153, 78, 0.6)', 'rgba(117, 209, 215, 0.6)'],
borderColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,0.4)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)'],
hoverBackgroundColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,1)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)']
}]
};
new Chart(document.getElementById('chart_Sculpture'), {
type: 'bar',
data: data_Sculpture ,
options: {
scales: {
y: {
beginAtZero: true,
min: 0,
max: 100,
ticks: {
stepSize: 20
}
},
x: {
display: false
}
},
plugins: {
legend: {
display: false
},
tooltip: {
}
}
}
});
// "data_Portraits " chart
const data_Portraits = {
labels: ['Fuyu-8B', 'Qwen-VL-7B', 'InstructBLIP-T5-XXL', 'LLaVA-1.5-13B', 'BLIP-2 FLAN-T5-XXL', 'GPT-4V'],
datasets: [{
data: [20.9, 52.7, 46.2, 54.9, 47.3, 70.3],
backgroundColor: ['rgba(196, 123, 160, 0.6)', 'rgba(245, 123, 113, 0.6)', 'rgba(255, 208, 80, 0.6)', 'rgba(110, 194, 134, 0.6)', 'rgba(255, 153, 78, 0.6)', 'rgba(117, 209, 215, 0.6)'],
borderColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,0.4)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)'],
hoverBackgroundColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,1)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)']
}]
};
new Chart(document.getElementById('chart_Portraits'), {
type: 'bar',
data: data_Portraits ,
options: {
scales: {
y: {
beginAtZero: true,
min: 0,
max: 100,
ticks: {
stepSize: 20
}
},
x: {
display: false
}
},
plugins: {
legend: {
display: false
},
tooltip: {
}
}
}
});
// "data_Screenshots " chart
const data_Screenshots = {
labels: ['Fuyu-8B', 'Qwen-VL-7B', 'InstructBLIP-T5-XXL', 'LLaVA-1.5-13B', 'BLIP-2 FLAN-T5-XXL', 'GPT-4V'],
datasets: [{
data: [38.6, 35.7, 38.6, 34.3, 47.1, 65.7],
backgroundColor: ['rgba(196, 123, 160, 0.6)', 'rgba(245, 123, 113, 0.6)', 'rgba(255, 208, 80, 0.6)', 'rgba(110, 194, 134, 0.6)', 'rgba(255, 153, 78, 0.6)', 'rgba(117, 209, 215, 0.6)'],
borderColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,0.4)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)'],
hoverBackgroundColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,1)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)']
}]
};
new Chart(document.getElementById('chart_Screenshots'), {
type: 'bar',
data: data_Screenshots ,
options: {
scales: {
y: {
beginAtZero: true,
min: 0,
max: 100,
ticks: {
stepSize: 20
}
},
x: {
display: false
}
},
plugins: {
legend: {
display: false
},
tooltip: {
}
}
}
});
// "data_Other " chart
const data_Other = {
labels: ['Fuyu-8B', 'Qwen-VL-7B', 'InstructBLIP-T5-XXL', 'LLaVA-1.5-13B', 'BLIP-2 FLAN-T5-XXL', 'GPT-4V'],
datasets: [{
data: [28.3, 38.3, 50.0, 51.7, 58.3, 68.3],
backgroundColor: ['rgba(196, 123, 160, 0.6)', 'rgba(245, 123, 113, 0.6)', 'rgba(255, 208, 80, 0.6)', 'rgba(110, 194, 134, 0.6)', 'rgba(255, 153, 78, 0.6)', 'rgba(117, 209, 215, 0.6)'],
borderColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,0.4)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)'],
hoverBackgroundColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,1)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)']
}]
};
new Chart(document.getElementById('chart_Other'), {
type: 'bar',
data: data_Other ,
options: {
scales: {
y: {
beginAtZero: true,
min: 0,
max: 100,
ticks: {
stepSize: 20
}
},
x: {
display: false
}
},
plugins: {
legend: {
display: false
},
tooltip: {
}
}
}
});
// "data_Poster " chart
const data_Poster = {
labels: ['Fuyu-8B', 'Qwen-VL-7B', 'InstructBLIP-T5-XXL', 'LLaVA-1.5-13B', 'BLIP-2 FLAN-T5-XXL', 'GPT-4V'],
datasets: [{
data: [38.6, 50.9, 52.6, 61.4, 64.9, 80.7],
backgroundColor: ['rgba(196, 123, 160, 0.6)', 'rgba(245, 123, 113, 0.6)', 'rgba(255, 208, 80, 0.6)', 'rgba(110, 194, 134, 0.6)', 'rgba(255, 153, 78, 0.6)', 'rgba(117, 209, 215, 0.6)'],
borderColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,0.4)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)'],
hoverBackgroundColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,1)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)']
}]
};
new Chart(document.getElementById('chart_Poster'), {
type: 'bar',
data: data_Poster ,
options: {
scales: {
y: {
beginAtZero: true,
min: 0,
max: 100,
ticks: {
stepSize: 20
}
},
x: {
display: false
}
},
plugins: {
legend: {
display: false
},
tooltip: {
}
}
}
});
// "data_IconsAndSymbols " chart
const data_IconsAndSymbols = {
labels: ['Fuyu-8B', 'Qwen-VL-7B', 'InstructBLIP-T5-XXL', 'LLaVA-1.5-13B', 'BLIP-2 FLAN-T5-XXL', 'GPT-4V'],
datasets: [{
data: [23.8, 66.7, 57.1, 59.5, 59.5, 78.6],
backgroundColor: ['rgba(196, 123, 160, 0.6)', 'rgba(245, 123, 113, 0.6)', 'rgba(255, 208, 80, 0.6)', 'rgba(110, 194, 134, 0.6)', 'rgba(255, 153, 78, 0.6)', 'rgba(117, 209, 215, 0.6)'],
borderColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,0.4)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)'],
hoverBackgroundColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,1)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)']
}]
};
new Chart(document.getElementById('chart_IconsAndSymbols'), {
type: 'bar',
data: data_IconsAndSymbols ,
options: {
scales: {
y: {
beginAtZero: true,
min: 0,
max: 100,
ticks: {
stepSize: 20
}
},
x: {
display: false
}
},
plugins: {
legend: {
display: false
},
tooltip: {
}
}
}
});
// "data_HistoricalTimelines " chart
const data_HistoricalTimelines = {
labels: ['Fuyu-8B', 'Qwen-VL-7B', 'InstructBLIP-T5-XXL', 'LLaVA-1.5-13B', 'BLIP-2 FLAN-T5-XXL', 'GPT-4V'],
datasets: [{
data: [30.0, 36.7, 40.0, 43.3, 43.3, 63.3],
backgroundColor: ['rgba(196, 123, 160, 0.6)', 'rgba(245, 123, 113, 0.6)', 'rgba(255, 208, 80, 0.6)', 'rgba(110, 194, 134, 0.6)', 'rgba(255, 153, 78, 0.6)', 'rgba(117, 209, 215, 0.6)'],
borderColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,0.4)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)'],
hoverBackgroundColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,1)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)']
}]
};
new Chart(document.getElementById('chart_HistoricalTimelines'), {
type: 'bar',
data: data_HistoricalTimelines ,
options: {
scales: {
y: {
beginAtZero: true,
min: 0,
max: 100,
ticks: {
stepSize: 20
}
},
x: {
display: false
}
},
plugins: {
legend: {
display: false
},
tooltip: {
}
}
}
});
// "data_3DRenderings " chart
const data_3DRenderings = {
labels: ['Fuyu-8B', 'Qwen-VL-7B', 'InstructBLIP-T5-XXL', 'LLaVA-1.5-13B', 'BLIP-2 FLAN-T5-XXL', 'GPT-4V'],
datasets: [{
data: [33.3, 28.6, 57.1, 38.1, 47.6, 47.6],
backgroundColor: ['rgba(196, 123, 160, 0.6)', 'rgba(245, 123, 113, 0.6)', 'rgba(255, 208, 80, 0.6)', 'rgba(110, 194, 134, 0.6)', 'rgba(255, 153, 78, 0.6)', 'rgba(117, 209, 215, 0.6)'],
borderColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,0.4)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)'],
hoverBackgroundColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,1)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)']
}]
};
new Chart(document.getElementById('chart_3DRenderings'), {
type: 'bar',
data: data_3DRenderings ,
options: {
scales: {
y: {
beginAtZero: true,
min: 0,
max: 100,
ticks: {
stepSize: 20
}
},
x: {
display: false
}
},
plugins: {
legend: {
display: false
},
tooltip: {
}
}
}
});
// "data_DNASequences " chart
const data_DNASequences = {
labels: ['Fuyu-8B', 'Qwen-VL-7B', 'InstructBLIP-T5-XXL', 'LLaVA-1.5-13B', 'BLIP-2 FLAN-T5-XXL', 'GPT-4V'],
datasets: [{
data: [20.0, 45.0, 25.0, 25.0, 45.0, 55.0],
backgroundColor: ['rgba(196, 123, 160, 0.6)', 'rgba(245, 123, 113, 0.6)', 'rgba(255, 208, 80, 0.6)', 'rgba(110, 194, 134, 0.6)', 'rgba(255, 153, 78, 0.6)', 'rgba(117, 209, 215, 0.6)'],
borderColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,0.4)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)'],
hoverBackgroundColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,1)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)']
}]
};
new Chart(document.getElementById('chart_DNASequences'), {
type: 'bar',
data: data_DNASequences ,
options: {
scales: {
y: {
beginAtZero: true,
min: 0,
max: 100,
ticks: {
stepSize: 20
}
},
x: {
display: false
}
},
plugins: {
legend: {
display: false
},
tooltip: {
}
}
}
});
// "data_Landscapes " chart
const data_Landscapes = {
labels: ['Fuyu-8B', 'Qwen-VL-7B', 'InstructBLIP-T5-XXL', 'LLaVA-1.5-13B', 'BLIP-2 FLAN-T5-XXL', 'GPT-4V'],
datasets: [{
data: [43.8, 43.8, 50.0, 31.2, 62.5, 68.8],
backgroundColor: ['rgba(196, 123, 160, 0.6)', 'rgba(245, 123, 113, 0.6)', 'rgba(255, 208, 80, 0.6)', 'rgba(110, 194, 134, 0.6)', 'rgba(255, 153, 78, 0.6)', 'rgba(117, 209, 215, 0.6)'],
borderColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,0.4)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)'],
hoverBackgroundColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,1)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)']
}]
};
new Chart(document.getElementById('chart_Landscapes'), {
type: 'bar',
data: data_Landscapes ,
options: {
scales: {
y: {
beginAtZero: true,
min: 0,
max: 100,
ticks: {
stepSize: 20
}
},
x: {
display: false
}
},
plugins: {
legend: {
display: false
},
tooltip: {
}
}
}
});
// "data_LogosAndBranding " chart
const data_LogosAndBranding = {
labels: ['Fuyu-8B', 'Qwen-VL-7B', 'InstructBLIP-T5-XXL', 'LLaVA-1.5-13B', 'BLIP-2 FLAN-T5-XXL', 'GPT-4V'],
datasets: [{
data: [21.4, 57.1, 64.3, 35.7, 50.0, 85.7],
backgroundColor: ['rgba(196, 123, 160, 0.6)', 'rgba(245, 123, 113, 0.6)', 'rgba(255, 208, 80, 0.6)', 'rgba(110, 194, 134, 0.6)', 'rgba(255, 153, 78, 0.6)', 'rgba(117, 209, 215, 0.6)'],
borderColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,0.4)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)'],
hoverBackgroundColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,1)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)']
}]
};
new Chart(document.getElementById('chart_LogosAndBranding'), {
type: 'bar',
data: data_LogosAndBranding ,
options: {
scales: {
y: {
beginAtZero: true,
min: 0,
max: 100,
ticks: {
stepSize: 20
}
},
x: {
display: false
}
},
plugins: {
legend: {
display: false
},
tooltip: {
}
}
}
});
// "data_Advertisements " chart
const data_Advertisements = {
labels: ['Fuyu-8B', 'Qwen-VL-7B', 'InstructBLIP-T5-XXL', 'LLaVA-1.5-13B', 'BLIP-2 FLAN-T5-XXL', 'GPT-4V'],
datasets: [{
data: [30.0, 60.0, 50.0, 60.0, 70.0, 100.0],
backgroundColor: ['rgba(196, 123, 160, 0.6)', 'rgba(245, 123, 113, 0.6)', 'rgba(255, 208, 80, 0.6)', 'rgba(110, 194, 134, 0.6)', 'rgba(255, 153, 78, 0.6)', 'rgba(117, 209, 215, 0.6)'],
borderColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,0.4)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)'],
hoverBackgroundColor: ['rgba(196, 123, 160, 1)', 'rgba(245, 123, 113,1)', 'rgba(255, 208, 80, 1)', 'rgba(110, 194, 134, 1)', 'rgba(255, 153, 78, 1)', 'rgba(117, 209, 215, 1)']
}]
};
new Chart(document.getElementById('chart_Advertisements'), {
type: 'bar',
data: data_Advertisements ,
options: {
scales: {
y: {
beginAtZero: true,
min: 0,
max: 100,
ticks: {
stepSize: 20
}
},
x: {
display: false
}
},
plugins: {
legend: {
display: false
},
tooltip: {
}
}
}
});
});
</script>
<style>
.publication-links {
/* 在默认情况下,水平排列 */
display: flex;
}
/* 在屏幕宽度小于600px时,竖直排列 */
@media only screen and (max-width: 600px) {
.publication-links {
display: flex;
flex-direction: column; /* 将元素竖直排列 */
}
}
.hidden {
display: none;
}
.sortable:hover {
cursor: pointer;
}
.asc::after {
content: ' ↑';
}
.desc::after {
content: ' ↓';
}
#toggleButton {
background-color: #ffffff;
border: 1px solid #dddddd;
color: #555555;
padding: 10px 20px;
text-align: center;
text-decoration: none;
display: inline-block;
font-size: 14px;
margin: 4px 2px;
cursor: pointer;
border-radius: 25px;
box-shadow: 0 4px 8px 0 rgba(0,0,0,0.2);
transition-duration: 0.4s;
}
#toggleButton:hover {
box-shadow: 0 12px 16px 0 rgba(0,0,0,0.24), 0 17px 50px 0 rgba(0,0,0,0.19); /* 鼠标悬停时的阴影效果 */
}
table {
border-collapse: collapse;
width: 100%;
margin-top: 5px;
border: 1px solid #ddd;
font-size: 14px;
border-left: none;
border-right: none;
overflow-x: auto; /* 将 overflow-x 设置为 auto */
}
th, td {
text-align: left;
padding: 8px;
border-left: none;
border-right: none;
}
th {
background-color: #f2f2f2;
border-bottom: 2px solid #ddd;
border-left: none;
border-right: none;
}
td:hover {background-color: #ffffff;}
/* 去掉第二行和第三行之间的横线 */
tr:nth-child(1) td {
border-bottom: none;
}
tr:nth-child(2) td {
border-bottom: none;
}
tr:nth-child(3) td {
border-bottom: none;
}
tr:nth-child(4) td {
border-bottom: none;
}
.dashed-border {
border-top: 2px dashed #ccc; /* 调整间隔宽度和颜色 */
/* border-image: linear-gradient(to right, #ccc 25%, transparent 25%) 1 1; */
}
.centered-span {
display: flex;
align-items: center;
justify-content: center; /* 水平居中 */
height: 100%; /* 让 span 高度充满单元格 */
}
tr:nth-child(7) td {
border-bottom: none;
}
tr:nth-child(8) td {
border-bottom: none;
}
tr:nth-child(9) td {
border-bottom: none;
}
tr:nth-child(10) td {
border-bottom: none;
}
tr:nth-child(11) td {
border-bottom: none;
}
tr:nth-child(12) td {
border-bottom: none;
}
tr:nth-child(13) td {
border-bottom: none;
}
tr:nth-child(14) td {
border-bottom: none;
}
tr:nth-child(15) td {
border-bottom: none;
}
tr:nth-child(16) td {
border-bottom: none;
}
tr:nth-child(17) td {
border-bottom: none;
}
tr:nth-child(18) td {
border-bottom: none;
}
tr:nth-child(19) td {
border-bottom: none;
}
tr:nth-child(20) td {
border-bottom: none;
}
tr:nth-child(21) td {
border-bottom: none;
}
tr:nth-child(22) td {
border-bottom: none;
}
tr:nth-child(23) td {
border-bottom: none;
}
tr:nth-child(24) td {
border-bottom: none;
}
tr:nth-child(25) td {
border-bottom: none;
}
tr:nth-child(26) td {
border-bottom: none;
}
tr:nth-child(29) td {
border-bottom: none;
}
tr:nth-child(30) td {
border-bottom: none;
}
tr:nth-child(31) td {
border-bottom: none;
}
tr:nth-child(32) td {
border-bottom: none;
}
tr:nth-child(33) td {
border-bottom: none;
}
tr:nth-child(36) td {
border-bottom: none;
}
tr:nth-child(37) td {
border-bottom: none;
}
tr:nth-child(38) td {
border-bottom: none;
}
tr:nth-child(39) td {
border-bottom: none;
}
tr:nth-child(40) td {
border-bottom: none;
}
tr:nth-child(41) td {
border-bottom: none;
}
tr:nth-child(42) td {
border-bottom: none;
}
tr:nth-child(43) td {
border-bottom: none;
}
tr:nth-child(44) td {
border-bottom: none;
}
tr:nth-child(45) td {
border-bottom: none;
}
tr:nth-child(46) td {
border-bottom: none;
}
tr:nth-child(47) td {
border-bottom: none;
}
tr:nth-child(48) td {
border-bottom: none;
}
tr:nth-child(49) td {
border-bottom: none;
}
tr:nth-child(50) td {
border-bottom: none;
}
tr:nth-child(53) td {
border-bottom: none;
}
tr:nth-child(54) td {
border-bottom: none;
}
tr:nth-child(55) td {
border-bottom: none;
}
</style>
</body>
</html> |