{"id":"W4415595662","doi":"10.1016/j.ipm.2025.104449","title":"Leveraging historical information to boost retrieval-augmented generation in conversations","year":2025,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Topic Modeling","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Amazon","keywords":"Boosting (machine learning); Context (archaeology); Text generation; Information system; Information needs","routes":{"ca_aff":true,"ca_fund":true,"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":[0.003744476,0.002112132,0.001601028,0.001733063,0.001024092,0.001688529,0.002166729,0.00189074,0.003693851],"category_scores_gemma":[0.01531648,0.0007297658,0.001020009,0.001092046,0.0006435859,0.003604884,0.002292831,0.002487734,0.002782021],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007391302,"about_ca_system_score_gemma":0.001437106,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005181458,"about_ca_topic_score_gemma":0.01065809,"domain_scores_codex":[0.9980136,0.0008771616,0.00008618276,0.0005516905,0.0002632539,0.0002080959],"domain_scores_gemma":[0.9928681,0.005110751,0.0002101976,0.0008547804,0.0006627479,0.0002933598],"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":[0.001664143,0.0008970941,0.01336561,0.0007172593,0.0003138094,0.000411883,0.001533674,0.111805,0.03015727,0.003458022,0.01954576,0.8161304],"study_design_scores_gemma":[0.0001130436,0.000326483,0.002677716,0.0000586789,0.0001633644,0.000273588,0.0003380188,0.9704289,0.01258367,0.006911816,0.00605003,0.00007465597],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.215006,0.007438358,0.7400053,0.002058763,0.0006719987,0.0006125706,0.001591759,0.02344829,0.009166976],"genre_scores_gemma":[0.7883257,0.0007658594,0.1998836,0.0008047422,0.0004733171,0.000328532,0.0033179,0.0007850639,0.005315188],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005181458,"threshold_uncertainty_score":0.01980287,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02004362624849737,"score_gpt":0.2488657579690393,"score_spread":0.2288221317205419,"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."}}