{"id":"W4385571655","doi":"10.18653/v1/2023.findings-acl.46","title":"The Web Can Be Your Oyster for Improving Language Models","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"Renmin University of China; National Natural Science Foundation of China","keywords":"Computer science; Salient; Language model; Task (project management); Information retrieval; ENCODE; Machine learning; Search engine; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003127638,0.00006074297,0.00005610561,0.00003337735,0.0001579983,0.0001726371,0.0006108283,0.00002497296,0.000001978343],"category_scores_gemma":[0.0000248268,0.00003874718,0.00004132466,0.0001274881,0.000008191982,0.0001643076,0.0002397077,0.00004701412,0.00001071739],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001758794,"about_ca_system_score_gemma":0.00005084632,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001604956,"about_ca_topic_score_gemma":0.0002897838,"domain_scores_codex":[0.9992841,0.00001253375,0.0001102141,0.0002051979,0.0001289625,0.0002589261],"domain_scores_gemma":[0.9993553,0.00009941884,0.00002377746,0.0004552539,0.00002860294,0.0000377076],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000005196179,0.0000134632,0.00005426362,0.00006128252,0.00002595634,0.00001673455,0.01326318,0.0148245,0.0137053,0.5812763,0.01028478,0.366469],"study_design_scores_gemma":[0.0001067339,0.00000819017,0.000006176636,0.000002008186,0.000001335208,0.000001637233,0.0003886258,0.993576,0.0004747892,0.004114456,0.001258473,0.0000615624],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02582776,0.00003611643,0.9623298,0.008089076,0.0003348144,0.0001883908,0.000003289083,0.0003777785,0.002812969],"genre_scores_gemma":[0.9470184,0.000003170746,0.03622026,0.0008818408,0.0001218918,0.00005110488,0.00000143214,0.000009869437,0.01569205],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9787515,"threshold_uncertainty_score":0.1664743,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05366418091734578,"score_gpt":0.280569888942892,"score_spread":0.2269057080255462,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}