{"id":"W4404782892","doi":"10.18653/v1/2024.emnlp-main.250","title":"PromptReps: Prompting Large Language Models to Generate Dense and Sparse Representations for Zero-Shot Document Retrieval","year":2024,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; University of Waterloo","keywords":"Zero (linguistics); Computer science; Shot (pellet); Natural language processing; Artificial intelligence; Language model; Information retrieval; Linguistics; Materials science","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":[],"consensus_categories":[],"category_scores_codex":[0.0004986498,0.0001227894,0.0001223618,0.0001129066,0.0001268282,0.0005376433,0.0002562071,0.00003813579,0.00001447621],"category_scores_gemma":[0.00004415008,0.000106414,0.00004432163,0.0002427244,0.000008187165,0.0005702439,0.0003081812,0.00007711315,0.00001724302],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000416605,"about_ca_system_score_gemma":0.00006495757,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000057785,"about_ca_topic_score_gemma":0.00002766085,"domain_scores_codex":[0.998566,0.00003131172,0.0002463304,0.0006339001,0.0002028306,0.0003196156],"domain_scores_gemma":[0.9992558,0.00008252671,0.00002514892,0.0004497,0.00006159006,0.0001251795],"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":[0.00004223718,0.00009777306,0.00009943743,0.0003370747,0.0001219344,0.0001657511,0.04158344,0.03821937,0.03406037,0.8438094,0.006379644,0.0350836],"study_design_scores_gemma":[0.0001993712,0.00004194034,0.00001163766,0.00004375268,0.00001011756,0.00001881675,0.0001849848,0.9769386,0.008104574,0.01359867,0.0006919473,0.0001556151],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1923651,0.0002701475,0.8041018,0.001456352,0.0002087852,0.0006366539,0.000006553023,0.0002769668,0.0006775584],"genre_scores_gemma":[0.6761546,0.000005905935,0.3194999,0.0003270731,0.0001019765,0.00007460672,0.000004445733,0.00001312444,0.003818384],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9387192,"threshold_uncertainty_score":0.5184507,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06476820452331428,"score_gpt":0.3327538031602711,"score_spread":0.2679855986369569,"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."}}