{"id":"W6947999492","doi":"10.48448/chfw-wa16","title":"ChatRetriever: Adapting Large Language Models for Generalized and Robust Conversational Dense Retrieval","year":2024,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Robustness (evolution); Language model; Generalization; Rewriting; Session (web analytics); Interpretation (philosophy); Training set","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002115206,0.001399207,0.001344052,0.0008777425,0.000553416,0.001408916,0.002977345,0.00141979,0.003671675],"category_scores_gemma":[0.0082729,0.0006101211,0.001198942,0.0006423591,0.0007665298,0.003522461,0.00303093,0.002317994,0.003432526],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007551141,"about_ca_system_score_gemma":0.001436889,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007461654,"about_ca_topic_score_gemma":0.01229907,"domain_scores_codex":[0.9985604,0.000527099,0.00008514275,0.0004387436,0.0002756253,0.0001130635],"domain_scores_gemma":[0.9967989,0.001568402,0.0001313199,0.001011954,0.0003659742,0.0001235015],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005642461,0.0004769111,0.00179349,0.0005322815,0.0003002976,0.0002840515,0.0007124599,0.1540642,0.05344963,0.007675288,0.01669138,0.7634557],"study_design_scores_gemma":[0.00003538068,0.0001174971,0.0002285177,0.0000120433,0.00003366014,0.00009928558,0.0001042585,0.9757468,0.01058221,0.00830075,0.004690009,0.00004969094],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02264031,0.0006978761,0.9492441,0.0002211907,0.00008720602,0.0001922174,0.0004736275,0.02481959,0.001623805],"genre_scores_gemma":[0.3683968,0.0004139002,0.6170982,0.000666288,0.0001468869,0.0005079139,0.002929556,0.002334961,0.007505525],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007461654,"threshold_uncertainty_score":0.01483649,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03032577417322737,"score_gpt":0.3014703699196813,"score_spread":0.2711445957464539,"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."}}