--- model-index: - name: robinlee99/long-t5-tglobal-large-AERA results: [] language: - en base_model: google/long-t5-tglobal-large license: apache-2.0 widget: - text: "[Question]: \nA group of students wrote the following procedure for their investigation.\nProcedure:\n1.Determine the mass of four different samples.\n2.Pour vinegar in each of four separate, but identical, containers.\n3.Place a sample of one material into one container and label. Repeat with remaining samples, placing a single\nsample into a single container.\n4.After 24 hours, remove the samples from the containers and rinse each sample with distilled water.\n5.Allow the samples to sit and dry for 30 minutes.\n6.Determine the mass of each sample.\nThe students's data are recorded in the table below.\nA table contains four columns: Sample, Starting Mass (g), Ending Mass (g), Difference in Mass (g).\nThe sample for the first row is Marble, with 9.8 Starting Mass, 9.4 Ending Mass and -0.4 for Difference in\nMass.\nThe sample for the second row is Limestone, with 10.4 Starting Mass, 9.1 Ending Mass and -1.3 for Difference\nin Mass.\nThe sample for the third row is Wood, with 11.2 Starting Mass, 11.2 Ending Mass and 0.0 for Difference in Mass.\nThe sample for last row is Plastic, with 7.2 Starting Mass, 7.1 Ending Mass and -0.1 for Difference in Mass.\nAfter reading the group's procedure, describe what additional information you would need in order to replicate\nthe experiment.\nMake sure to include at least three pieces of information.\n\n[Key Elements]:\nNeeded Information:\nYou need to know how much vinegar was used in each container.\nYou need to know what type of vinegar was used in each container.\nYou need to know what materials to test.\nYou need to know what size/surface area of materials should be used.\nYou need to know how long each sample was rinsed in distilled water.\nYou need to know what drying method to use.\nYou need to know what size/type of container to use.\nOther acceptable responses.\n\n[Marking Rubric]:\n3 points: The response describes three additional pieces of information that would be needed to accurately\nreplicate the experiment;\n2 points: The response describes two additional pieces of information that would be needed to accurately\nreplicate the experiment;\n1 point: The response describes one additional piece of information that would be needed to accurately\nreplicate the experiment;\n0 point: The response describes little or no accurate or relevant information from the acid rain investigation.\n\n[Student Answer]: The procedures I think they should have included inorder for me to replicate the experiment would be how different samples did they used for each? What tool did they use to determine the mass.\n[Score and Rationale]:" example_title: "AES Eassy Set 1" - text: "[Question]: \nA student performed the following investigation to test four different polymer plastics for stretchability.\nProcedure:\n1. Take a sample of one type of plastic, and measure its length.\n2. Tape the top edge of the plastic sample to a table so that it is hanging freely down the side of the table.\n3. Attach a clamp to the bottom edge of the plastic sample.\n4. Add weights to the clamp and allow them to hang for five minutes.\n5. Remove the weights and clamp, and measure the length of the plastic types.\n6. Repeat the procedure exactly for the remaining three plastic samples.\n7. Perform a second trial (T2) exactly like the first trial (T1).\nThe student recorded the following data from the investigation.\nThe table shows the amount of stretch (in millimeters) for four different types of plastic, labeled as A, B,\nC, and D, when subjected to two different stretching forces, labeled as T1 and T2.\nFor plastic type A, it stretched 10mm under T1 and 12mm under T2.\nFor plastic type B, it stretched 22mm under T1 and 23mm under T2.\nFor plastic type C, it stretched 14mm under T1 and 13mm under T2.\nLastly, for plastic type D, it stretched 20mm under both T1 and T2.\na. Draw a conclusion based on the student’s data.\nb. Describe two ways the student could have improved the experimental design and/or validity of the results.\n\n[Key Elements]:\nConclusions:\nPlastic sample B has more stretchability than the other polymer plastics.\nPlastic sample A has the least amount of stretchability compared to the other polymer plastics.\nNot all polymer plastics have the same stretchability.\nDifferent polymer plastics have different stretchability (and are therefore suited for different applications).\nA reasonable conclusion cannot be drawn due to procedural errors.\nOther reasonable conclusions \n\nExperimental Design Improvements:\nProvide the before and after measurements for length (Did the samples all start out the same size?).\nMake sure the samples are all of the same thickness.\nVariations in thickness could have caused variations in stretchability.\nPerform additional trials.\nSome of the samples have similar stretchability (A and C, B and D).\nTwo trials may not be enough to conclusively state that one is more stretchable than the other.\nIndicate how many weights were added to the clamps (Was it the same number for each sample?).\nOther acceptable responses\n\n[Marking Rubric]:\n3 points: The response draws a valid conclusion supported by the student’s data and describes two ways the\nstudent could have improved the experimental design and/or the validity of the results;\n2 points: The response draws a valid conclusion supported by the student’s data and describes one way the\nstudent could have improved the experimental design and/or the validity of the results. -or- The response\ndescribes two ways the student could have improved the experimental design and/or the validity of the results\nbut fails to draw or incorrectly draws a conclusion from the student’s data;\n1 point: The response draws a valid conclusion supported by the student’s data but fails to describe, or\nincorrectly describes, how the student could have improved the experimental design and/or the validity of the\nresults. -or- The response describes one way the student could have improved the experimental design and/or\nthe validity of the results but fails to draw or incorrectly draws a conclusion from the student's data.;\n0 points: The response provides little or no correct information from the polymer investigation.\n\n[Student Answer]: Based on the students data I can conclude that plastic type B has the largest amount stretched. Two ways that the student could have improved the experimental decison is by allowing the weights to hang longer to see if the plastic would stretch more. Another way he could have improved his experiment is by doing a third trials to really be sure that his results are correct.\n[Score and Rationale]:" example_title: "AES Eassy Set 2" - text: "[Question]: \nStarting with mRNA leaving the nucleus, list and describe four major steps involved in protein synthesis.\n\n[Key Elements]:\nmRNA exits nucleus via nuclear pore.\nmRNA travels through the cytoplasm to the ribosome or enters the rough endoplasmic reticulum.\nmRNA bases are read in triplets called codons (by rRNA).\ntRNA carrying the complementary (U=A, C+G) anticodon recognizes the complementary codon of the mRNA.\nThe corresponding amino acids on the other end of the tRNA are bonded to adjacent tRNA’s amino acids.\nA new corresponding amino acid is added to the tRNA.\nAmino acids are linked together to make a protein beginning with a START codon in the P site (initiation).\nAmino acids continue to be linked until a STOP codon is read on the mRNA in the A site (elongation and\ntermination).\n\n[Marking Rubric]:\n3 points: Four key elements;\n2 points: Three key elements;\n1 point: One or two key elements;\n0 points: Other.\n\n[Student Answer]: 1. tRNA tranfers it outside the nucleus to be matched with a ribosome2. The ribosome latches on to an amino acid.3. The codons match up4. It creates protein.\n[Score and Rationale]:" example_title: "AES Eassy Set 5" - text: "[Question]: \nList and describe three processes used by cells to control the movement of substances across the cell membrane.\n\n[Key elements]:\nSelective permeability is used by the cell membrane to allow certain substances to move across.\nPassive transport occurs when substances move from an area of higher concentration to an area of lower\nconcentration.\nOsmosis is the diffusion of water across the cell membrane.\nFacilitated diffusion occurs when the membrane controls the pathway for a particle to enter or leave a cell.\nActive transport occurs when a cell uses energy to move a substance across the cell membrane, and/or a\nsubstance moves from an area of low to high concentration, or against the concentration gradient.\nPumps are used to move charged particles like sodium and potassium ions through membranes using energy and\ncarrier proteins.\nMembrane-assisted transport occurs when the membrane of the vesicle fuses with the cell membrane forcing large\nmolecules out of the cell as in exocytosis.\nMembrane-assisted transport occurs when molecules are engulfed by the cell membrane as in endocytosis.\nMembrane-assisted transport occurs when vesicles are formed around large molecules as in phagocytosis.\nMembrane-assisted transport occurs when vesicles are formed around liquid droplets as in pinocytosis.\nProtein channels or channel proteins allow for the movement of specific molecules or substances into or out of\nthe cell.\n\n[Marking Rubric]:\n3 points: Three key elements;\n2 points: Two key elements;\n1 point: One key element;\n0 points: Other.\n\n[Student Answer]: osmosis- when water is diffused across a membrane from more concentrated to less concentrated.diffusion- materials that are crossed over from the membraneactive transport\n[Score and Rationale]:" example_title: "AES Eassy Set 6" --- NEW!! A newer version of this project is avaliable at [here](https://huggingface.co/collections/jiazhengli/mcts-with-preference-optimisation-670bdeaeada59c956f876092). # Model Card for long-t5-tglobal-large-AERA This repository provides a fine-tuned version of long-t5-tglobal-large, using our proposed [AERA](https://github.com/lijiazheng99/aera/tree/main) framework presented in the paper: [Distilling ChatGPT for Explainable Automated Student Answer Assessment](https://aclanthology.org/2023.findings-emnlp.399.pdf). ## Citation Information ```bibtex @inproceedings{li-etal-2023-distilling, title = "Distilling {C}hat{GPT} for Explainable Automated Student Answer Assessment", author = "Li, Jiazheng and Gui, Lin and Zhou, Yuxiang and West, David and Aloisi, Cesare and He, Yulan", editor = "Bouamor, Houda and Pino, Juan and Bali, Kalika", booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023", month = dec, year = "2023", address = "Singapore", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2023.findings-emnlp.399", doi = "10.18653/v1/2023.findings-emnlp.399", pages = "6007--6026", abstract = "Providing explainable and faithful feedback is crucial for automated student answer assessment. In this paper, we introduce a novel framework that explores using ChatGPT, a cutting-edge large language model, for the concurrent tasks of student answer scoring and rationale generation. We identify the appropriate instructions by prompting ChatGPT with different templates to collect the rationales, where inconsistent rationales are refined to align with marking standards. The refined ChatGPT outputs enable us to fine-tune a smaller language model that simultaneously assesses student answers and provides rationales. Extensive experiments on the benchmark dataset show that the proposed method improves the overall QWK score by 11{\%} compared to ChatGPT. Furthermore, our thorough analysis and human evaluation demonstrate that the rationales generated by our proposed method are comparable to those of ChatGPT. Our approach provides a viable solution to achieve explainable automated assessment in education", } ```