{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001977666,0.0009880851,0.000634438,0.001242162,0.0006160652,0.001303938,0.001317899,0.0009926249,0.002468447],"category_scores_gemma":[0.008659109,0.0004052621,0.001093116,0.0007729001,0.0006401761,0.0028834,0.001480452,0.00188438,0.001435613],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000916071,"about_ca_system_score_gemma":0.001725108,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006761593,"about_ca_topic_score_gemma":0.01033814,"domain_scores_codex":[0.9988284,0.0006361123,0.00007268674,0.0002402521,0.0001588088,0.00006381189],"domain_scores_gemma":[0.9970716,0.001823537,0.0001740471,0.0004197335,0.0003655019,0.0001455497],"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":[0.0009007282,0.000438512,0.007288398,0.0009245045,0.0002103414,0.0005718223,0.004380095,0.2683261,0.03665692,0.0610645,0.02291136,0.5963267],"study_design_scores_gemma":[0.00003108206,0.00008133258,0.0004230033,0.00002528931,0.00004045959,0.00009504082,0.0002088992,0.9640265,0.003089456,0.02617709,0.005769364,0.00003253032],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02325942,0.0007436211,0.9663902,0.0009037892,0.00006055686,0.000166364,0.0007837783,0.005840466,0.001851776],"genre_scores_gemma":[0.5255285,0.0004607514,0.4676085,0.0003750444,0.0001470154,0.0003903599,0.002264206,0.0004540189,0.002771692],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006761593,"threshold_uncertainty_score":0.01344442,"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."}}