{"id":"W4287887656","doi":"10.18653/v1/2022.naacl-main.114","title":"Same Neurons, Different Languages: Probing Morphosyntax in Multilingual Pre-trained Models","year":2022,"lang":"en","type":"article","venue":"Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","topic":"Topic Modeling","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Vetenskapsrådet; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Computer science; Linguistics; Artificial intelligence; Natural language processing; Philosophy","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":[0.0004297501,0.0001955559,0.0003886739,0.0001801499,0.0003023799,0.00004036648,0.003022351,0.0000414866,0.00000268352],"category_scores_gemma":[0.002155543,0.0001340898,0.0002245205,0.0005033227,0.000263748,0.00007024284,0.001997315,0.0004069814,7.832256e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002093066,"about_ca_system_score_gemma":0.00008405477,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002812083,"about_ca_topic_score_gemma":0.0001231141,"domain_scores_codex":[0.9979633,0.00004125437,0.0006195472,0.0003438728,0.0007757525,0.0002562794],"domain_scores_gemma":[0.9968129,0.0002632391,0.001908184,0.0003864254,0.0006133938,0.00001588614],"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":[0.00008560427,0.0004474082,0.1705584,0.0003623369,0.0002682229,9.388434e-7,0.02451815,0.2304727,0.009550393,0.5523335,0.00009482392,0.0113075],"study_design_scores_gemma":[0.001512776,0.0004211518,0.07905065,0.0002977607,0.0001494939,0.000006144696,0.01577752,0.7160572,0.02285339,0.1630906,0.00008801877,0.0006952699],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9954757,0.00005737162,0.001820672,0.00113489,0.0002532043,0.0007759821,0.0001354009,0.0001273064,0.0002194505],"genre_scores_gemma":[0.9948472,0.00000275679,0.004805365,0.00006330513,0.00002851445,0.00007727178,0.000004670913,0.00001562767,0.0001552584],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4855845,"threshold_uncertainty_score":0.561633,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01915628939806864,"score_gpt":0.2542868450759871,"score_spread":0.2351305556779185,"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."}}