{"id":"W4389519413","doi":"10.18653/v1/2023.findings-emnlp.86","title":"Large Language Models Know Your Contextual Search Intent: A Prompting Framework for Conversational Search","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":43,"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; Leverage (statistics); Conversation; Language model; Robustness (evolution); Human–computer interaction; Natural language processing; Artificial intelligence; Information retrieval; World Wide Web; Data science; Psychology; Communication","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":[0.001193357,0.0001196165,0.0001509494,0.0001685508,0.0001868747,0.0001821397,0.0007256462,0.00009439373,0.00008360192],"category_scores_gemma":[0.0001780995,0.0001103136,0.00007983002,0.000411881,0.00002577567,0.0004134183,0.000555591,0.0002602623,0.0001866022],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005699592,"about_ca_system_score_gemma":0.0001441958,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006408054,"about_ca_topic_score_gemma":0.00001152758,"domain_scores_codex":[0.9981451,0.00005997197,0.000248725,0.0004719526,0.0004751848,0.0005990489],"domain_scores_gemma":[0.9988071,0.0004202025,0.00003156708,0.0004137317,0.0002121267,0.0001152617],"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":[0.000008195296,0.0000289056,0.0001722388,0.00004070673,0.00002166991,0.000009175985,0.01547131,0.005682937,0.0002005142,0.9658694,0.0003886055,0.0121064],"study_design_scores_gemma":[0.0004056538,0.00003372954,0.00007483431,0.00004118639,0.000001844875,0.000003290866,0.004235198,0.96891,0.0005132675,0.02540789,0.0002421645,0.0001308695],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05017467,0.00004541727,0.9453431,0.002175187,0.0001951816,0.0004444464,0.00001617563,0.0004599507,0.001145875],"genre_scores_gemma":[0.8082656,0.000004006881,0.188279,0.0003811884,0.0001632174,0.00005616112,0.00001784086,0.0000144433,0.002818605],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9632272,"threshold_uncertainty_score":0.4498456,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1060073351371927,"score_gpt":0.3566575900217333,"score_spread":0.2506502548845406,"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."}}