{"id":"W4396820721","doi":"10.48550/arxiv.2404.18424","title":"PromptReps: Prompting Large Language Models to Generate Dense and Sparse Representations for Zero-Shot Document Retrieval","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"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; Information retrieval; Linguistics; Philosophy; Chemistry","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001381275,0.001459993,0.001278451,0.0009835463,0.0004577822,0.001176129,0.00230658,0.001359004,0.005171989],"category_scores_gemma":[0.005548207,0.0005439474,0.001051636,0.0008787853,0.0007963345,0.003788663,0.002461748,0.00196992,0.004596237],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008069597,"about_ca_system_score_gemma":0.001326373,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004392797,"about_ca_topic_score_gemma":0.008547316,"domain_scores_codex":[0.9990085,0.0003453635,0.00006001483,0.0002446986,0.0002440733,0.00009742584],"domain_scores_gemma":[0.9983187,0.0006551243,0.0001141303,0.0005390784,0.0002788735,0.00009416477],"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":[0.0006750699,0.00049915,0.001143482,0.0005517668,0.0001764771,0.0002911139,0.0003646862,0.07871855,0.03943756,0.01316375,0.04504955,0.8199289],"study_design_scores_gemma":[0.0001005808,0.0002414544,0.0002959561,0.00001740614,0.00003227474,0.0001498213,0.00008372565,0.9628185,0.01708909,0.01268718,0.006431402,0.00005262583],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02412989,0.0006391692,0.9509905,0.0003062185,0.0001735398,0.0001921863,0.00069864,0.02113379,0.001736091],"genre_scores_gemma":[0.3181489,0.0005598697,0.6587395,0.0007727569,0.0002913824,0.0005972408,0.006167916,0.001493271,0.01322929],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005171989,"threshold_uncertainty_score":0.01730204,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1266048190329702,"score_gpt":0.2514864844701213,"score_spread":0.1248816654371512,"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."}}