{"id":"W4285263440","doi":"10.18653/v1/2022.acl-long.129","title":"Probing as Quantifying Inductive Bias","year":2022,"lang":"en","type":"article","venue":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","topic":"Topic Modeling","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Max Planck ETH Center for Learning Systems; McGill University; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Inductive bias; Computer science; ENCODE; Variety (cybernetics); Task (project management); Bayesian probability; Artificial intelligence; Natural language processing; Range (aeronautics); Position paper; Multi-task learning; Machine learning","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002162863,0.0001838925,0.0002911663,0.0001216668,0.001042436,0.0001022685,0.001713917,0.00007301599,0.000002981626],"category_scores_gemma":[0.01364003,0.0001553442,0.0002877115,0.0006771279,0.00005787575,0.0001283809,0.00121265,0.0003774465,0.000001365486],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004413902,"about_ca_system_score_gemma":0.0002476514,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007620362,"about_ca_topic_score_gemma":0.000002937396,"domain_scores_codex":[0.9972214,0.00005885081,0.0006938143,0.0004031263,0.001288736,0.0003341179],"domain_scores_gemma":[0.9943447,0.0007510947,0.002134161,0.0001995018,0.002519839,0.00005075677],"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":[0.0000622341,0.0002260473,0.2084332,0.0003254829,0.0003036723,3.474453e-7,0.01307669,0.3848622,0.001580994,0.3885279,0.001627324,0.0009739126],"study_design_scores_gemma":[0.002295214,0.0004764826,0.04388166,0.0006760771,0.0003446936,0.00001965915,0.006434076,0.762248,0.006787101,0.1553702,0.02032397,0.001142834],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9532183,0.0001782513,0.009153674,0.005692846,0.008268338,0.002676874,0.0002887464,0.0003311996,0.02019177],"genre_scores_gemma":[0.9772654,6.587079e-7,0.02126691,0.0002299714,0.0002717848,0.00004570809,0.000004294537,0.00002322392,0.0008921053],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3773858,"threshold_uncertainty_score":0.9946685,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02919653589517536,"score_gpt":0.2628133028168727,"score_spread":0.2336167669216974,"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."}}