{"id":"W6891760304","doi":"10.48448/y8tv-6k23","title":"PromptReps: Prompting Large Language Models to Generate Dense and Sparse Representations for Zero-Shot Document Retrieval","year":2024,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Document retrieval; Ranking (information retrieval); Construct (python library); Embedding; Language model; Question answering; Security token; Document classification","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":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002426248,0.0005613185,0.0005158582,0.001531153,0.000365259,0.0008493573,0.0007164905,0.0002027285,0.0002678956],"category_scores_gemma":[0.000437303,0.000508869,0.00009467152,0.00188407,0.000491666,0.0004521722,0.0007093333,0.0003380551,0.001312601],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003822795,"about_ca_system_score_gemma":0.0006872097,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003490968,"about_ca_topic_score_gemma":0.0008719127,"domain_scores_codex":[0.9949645,0.00007829365,0.0005920925,0.002026172,0.001188203,0.001150772],"domain_scores_gemma":[0.9977943,0.00007464732,0.0003270875,0.001038569,0.0002745007,0.0004909158],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002339712,0.0004654866,0.00005162347,0.001016847,0.0003326836,0.0002492437,0.01397423,0.004567213,0.1145285,0.03258356,0.8296492,0.002347405],"study_design_scores_gemma":[0.00533131,0.001185413,0.00003188434,0.003880556,0.001280613,0.0003219191,0.008186341,0.6541213,0.02741754,0.04248186,0.2502601,0.005501116],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.1286843,0.01817102,0.2101766,0.005845077,0.008519725,0.05548215,0.02082665,0.01149714,0.5407973],"genre_scores_gemma":[0.08573873,0.00005095599,0.159275,0.0005311957,0.001217527,0.0005758019,0.0004771542,0.002100339,0.7500333],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.6495541,"threshold_uncertainty_score":0.9997363,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06875774127856793,"score_gpt":0.3702844002975418,"score_spread":0.3015266590189739,"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."}}