Spaces:
Running
Running
| [ | |
| { | |
| "dataset": "cola", | |
| "type": "task", | |
| "origin_acc": 85.9, | |
| "origin_prompt": "Determine if the grammar of the given sentence is 'Acceptable' or 'Unacceptable':", | |
| "atk_acc": 78.1, | |
| "atk_prompt": "Determinqe if the grmamar of the igven sentewnce is 'Acceptable' or 'Unacceptable':", | |
| "transfer_ori_acc": 77.5, | |
| "transfer_atk_acc": 54.7 | |
| }, | |
| { | |
| "dataset": "cola", | |
| "type": "role", | |
| "origin_acc": 86.1, | |
| "origin_prompt": "In your role as a grammar check tool, assess the following sentence and classify it as 'acceptable' if it is grammatically correct or 'unacceptable' if it is incorrect:", | |
| "atk_acc": 84.5, | |
| "atk_prompt": "In your role as a grammar check too, assess the following senttence and classify it as 'acceptable' if it is rgammatically correct or 'unacceptable' if it is incorroct:", | |
| "transfer_ori_acc": 75.7, | |
| "transfer_atk_acc": 75.1 | |
| }, | |
| { | |
| "dataset": "mrpc", | |
| "type": "task", | |
| "origin_acc": 87.25, | |
| "origin_prompt": "Can the given sentences be considered semantically identical? Please reply with 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 83.58, | |
| "atk_prompt": "Can the given sentences be consiedred semantically idePntical? Plaese reply with 'equivalent' or 'not_equivalent'. ", | |
| "transfer_ori_acc": 80.63725490196079, | |
| "transfer_atk_acc": 81.12745098039215 | |
| }, | |
| { | |
| "dataset": "mrpc", | |
| "type": "role", | |
| "origin_acc": 88.73, | |
| "origin_prompt": "As a sentence similarity evaluator, analyze the provided sentences and indicate if their meanings are 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 81.13, | |
| "atk_prompt": "A a sentWnce sidmilarity evaluator, analyze the provAded sentences and idnicate if their meanVngs are 'equivalent' or 'not_equivalent'. ", | |
| "transfer_ori_acc": 80.63725490196079, | |
| "transfer_atk_acc": 82.1078431372549 | |
| }, | |
| { | |
| "dataset": "qnli", | |
| "type": "task", | |
| "origin_acc": 94.0, | |
| "origin_prompt": "Given the question and context provided, determine if the answer can be inferred by choosing 'entailment' or 'not_entailment'.", | |
| "atk_acc": 93.8, | |
| "atk_prompt": "Given the question and context provided, deermine if the answer can be inferred by choosing 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 84.89999999999999, | |
| "transfer_atk_acc": 83.8 | |
| }, | |
| { | |
| "dataset": "qnli", | |
| "type": "role", | |
| "origin_acc": 94.2, | |
| "origin_prompt": "As a semantic researcher, evaluate whether the provided context supports the answer to the question and choose 'entailment' or 'not_entailment'.", | |
| "atk_acc": 93.3, | |
| "atk_prompt": "us a sAmantic researJcher, evZluate hwether the provided context suports the answer to the question and choose 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 89.1, | |
| "transfer_atk_acc": 80.2 | |
| }, | |
| { | |
| "dataset": "qqp", | |
| "type": "task", | |
| "origin_acc": 88.2, | |
| "origin_prompt": "Please indicate if the following pair of sentences share the same meaning by responding with 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 87.4, | |
| "atk_prompt": "qPlease indicate if the folloing pair of senFences share the same meaning by resopnding with 'equivalent' or 'not_equivalent'. ", | |
| "transfer_ori_acc": 87.1, | |
| "transfer_atk_acc": 87.4 | |
| }, | |
| { | |
| "dataset": "qqp", | |
| "type": "role", | |
| "origin_acc": 88.5, | |
| "origin_prompt": "As a tool for determining question equivalence, review the questions and categorize their similarity as either 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 87.3, | |
| "atk_prompt": "As a tool for determining question equivalence, review the questions and ategorize their similvarity as eitehr 'equivalent' or 'not_equivalent'. ", | |
| "transfer_ori_acc": 86.5, | |
| "transfer_atk_acc": 82.5 | |
| }, | |
| { | |
| "dataset": "rte", | |
| "type": "task", | |
| "origin_acc": 94.22, | |
| "origin_prompt": "Examine the pair of sentences and determine if they exhibit entailment or not_entailment. Answer with either 'entailment' or 'not_entailment'.", | |
| "atk_acc": 92.06, | |
| "atk_prompt": "Examine the pir of sentencs and determine if they exxibit entailment or not_entailment. Answer with eitfer 'entailment' or 'not_entailment'.", | |
| "transfer_ori_acc": 84.11552346570397, | |
| "transfer_atk_acc": 85.1985559566787 | |
| }, | |
| { | |
| "dataset": "rte", | |
| "type": "role", | |
| "origin_acc": 93.86, | |
| "origin_prompt": "As an instrument for entailment evaluation, consider the two sentences and determine if their relationship is 'entailment' or 'not_entailment'. Respond with 'entailment' or 'not_entailment':", | |
| "atk_acc": 92.78, | |
| "atk_prompt": "As an instrument for entailment evaluation, consider the two sentences and determine if their relationship is 'entailment' or 'not_entailment'. Respodn with 'entailment' or 'not_entailment':", | |
| "transfer_ori_acc": 85.5595667870036, | |
| "transfer_atk_acc": 85.5595667870036 | |
| }, | |
| { | |
| "dataset": "sst2", | |
| "type": "task", | |
| "origin_acc": 96.56, | |
| "origin_prompt": "Analyze the tone of this statement and respond with either 'positive' or 'negative':", | |
| "atk_acc": 95.64, | |
| "atk_prompt": "AnalyVe the tone of this statelent and resBond with etiher 'positive' or 'negative': ", | |
| "transfer_ori_acc": 95.06880733944955, | |
| "transfer_atk_acc": 94.03669724770643 | |
| }, | |
| { | |
| "dataset": "sst2", | |
| "type": "role", | |
| "origin_acc": 96.33, | |
| "origin_prompt": "As a sentiment classifier, determine whether the following text is 'positive' or 'negative'. Please classify:", | |
| "atk_acc": 95.76, | |
| "atk_prompt": "s a sentiment classifier, determine whether the following text is 'positive' or 'negative'. Please claSsify: ", | |
| "transfer_ori_acc": 94.4954128440367, | |
| "transfer_atk_acc": 94.83944954128441 | |
| }, | |
| { | |
| "dataset": "wnli", | |
| "type": "task", | |
| "origin_acc": 80.28, | |
| "origin_prompt": "Assess the connection between the following sentences and classify it as 'entailment' or 'not_entailment'.", | |
| "atk_acc": 76.06, | |
| "atk_prompt": "Nssess the connection between the fnollowing sentences and classify it as 'entailment' or 'not_entailment'.", | |
| "transfer_ori_acc": 61.97183098591549, | |
| "transfer_atk_acc": 59.154929577464785 | |
| }, | |
| { | |
| "dataset": "wnli", | |
| "type": "role", | |
| "origin_acc": 80.28, | |
| "origin_prompt": "Functioning as an entailment evaluation tool, analyze the provided sentences and decide if their relationship is 'entailment' or 'not_entailment':", | |
| "atk_acc": 76.06, | |
| "atk_prompt": "Functioning as an entailment ealuation tCol, aSalyze the provided sentences and decide if their relationship is 'entailment' or 'not_entailment':", | |
| "transfer_ori_acc": 61.97183098591549, | |
| "transfer_atk_acc": 63.38028169014085 | |
| }, | |
| { | |
| "dataset": "mmlu", | |
| "type": "task", | |
| "origin_acc": 52.84, | |
| "origin_prompt": "Please respond to the multiple-choice question about {} by selecting the appropriate answer: 'A', 'B', 'C', or 'D'.", | |
| "atk_acc": 51.95, | |
| "atk_prompt": "Pqlease respond to the multiple-choice question about {} by Aelecting the appropriate answer: 'A', 'B', 'C', or 'D'. ", | |
| "transfer_ori_acc": 45.0354609929078, | |
| "transfer_atk_acc": 44.148936170212764 | |
| }, | |
| { | |
| "dataset": "mmlu", | |
| "type": "role", | |
| "origin_acc": 53.19, | |
| "origin_prompt": "As an expert in {}, respond to the following multiple-choice question by selecting 'A', 'B', 'C', or 'D'.", | |
| "atk_acc": 51.77, | |
| "atk_prompt": "As an exert in {}, respond to the following multiple-choice question by selecting 'A', 'B', 'C', or 'D'.", | |
| "transfer_ori_acc": 44.680851063829785, | |
| "transfer_atk_acc": 44.50354609929078 | |
| }, | |
| { | |
| "dataset": "squad_v2", | |
| "type": "task", | |
| "origin_acc": 90.05, | |
| "origin_prompt": "Please derive the most fitting answer from the context. If there isn't an answer in the context, respond with 'unanswerable'.", | |
| "atk_acc": 89.05, | |
| "atk_prompt": "Plase derive the most fitting answer from the contetx. If there isn't an answer in the conteSt, respond with 'unanswerable'.", | |
| "transfer_ori_acc": 87.64992770387508, | |
| "transfer_atk_acc": 86.92265497660236 | |
| }, | |
| { | |
| "dataset": "squad_v2", | |
| "type": "role", | |
| "origin_acc": 90.05, | |
| "origin_prompt": "As a well-informed specialist familiar with the context, provide an answer to the question. If the context doesn't contain an answer, reply with 'unanswerable'.", | |
| "atk_acc": 87.88, | |
| "atk_prompt": "Ads a wekl-informed specialist familiar with the context, provide an answer to the question. If the ocntext doesn't contain an answer, relpy with 'unanswerable'.", | |
| "transfer_ori_acc": 87.54992770387507, | |
| "transfer_atk_acc": 87.32265497660234 | |
| }, | |
| { | |
| "dataset": "iwslt", | |
| "type": "task", | |
| "origin_acc": 0.17, | |
| "origin_prompt": "Convert the following sentence from its original {} language to the target language {}:", | |
| "atk_acc": 0.16, | |
| "atk_prompt": "CUonvert the following sentence from its origlinal {} lagnuage to the tarSet language {}:", | |
| "transfer_ori_acc": 0.13467663417075984, | |
| "transfer_atk_acc": 0.10997077164306443 | |
| }, | |
| { | |
| "dataset": "iwslt", | |
| "type": "role", | |
| "origin_acc": 0.18, | |
| "origin_prompt": "Assuming the role of an expert language translator, translate the given text from {} to {}:", | |
| "atk_acc": 0.16, | |
| "atk_prompt": "ssuming the role of an expert langQuage transljator, translate the gdven tet from {} to {}: ", | |
| "transfer_ori_acc": 0.13744908017105148, | |
| "transfer_atk_acc": 0.13909938313005743 | |
| }, | |
| { | |
| "dataset": "un_multi", | |
| "type": "task", | |
| "origin_acc": 0.32, | |
| "origin_prompt": "Please perform a translation of the given sentence, converting it from {} to {}:", | |
| "atk_acc": 0.31, | |
| "atk_prompt": "Palease perfor a translation of the given sentence, converting it from {} to {}:", | |
| "transfer_ori_acc": 0.2683567351751297, | |
| "transfer_atk_acc": 0.26905804971419894 | |
| }, | |
| { | |
| "dataset": "un_multi", | |
| "type": "role", | |
| "origin_acc": 0.32, | |
| "origin_prompt": "Assuming the responsibilities of a professional translator, translate the subsequent text passage from {} to {}:", | |
| "atk_acc": 0.26, | |
| "atk_prompt": "tssuming the responsibilities of a professional transator, translate the subsequent teIxt passVge from {} to {}: ", | |
| "transfer_ori_acc": 0.2675180643301751, | |
| "transfer_atk_acc": 0.2447573643430312 | |
| }, | |
| { | |
| "dataset": "math", | |
| "type": "task", | |
| "origin_acc": 14.37, | |
| "origin_prompt": "Determine the solution to this mathematical problem related to {}:", | |
| "atk_acc": 13.12, | |
| "atk_prompt": "Determine the solution to this matuhematical problem related to {}:", | |
| "transfer_ori_acc": 10.625, | |
| "transfer_atk_acc": 11.25 | |
| }, | |
| { | |
| "dataset": "math", | |
| "type": "role", | |
| "origin_acc": 15.0, | |
| "origin_prompt": "As a mathematics instructor, calculate the answer to the following problem related to {}:", | |
| "atk_acc": 12.5, | |
| "atk_prompt": "As a matShematics instrkuctor, calculate the answer to the following problem related to {}: ", | |
| "transfer_ori_acc": 11.875, | |
| "transfer_atk_acc": 13.125 | |
| } | |
| ] |