{"id":"W4415155604","doi":"10.1007/978-981-95-3358-9_33","title":"Integrating Information Retrieval and LLMs: A Document Retrieval Chatbot in Education Settings","year":2025,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"","keywords":"Chatbot; Relevance (law); Pipeline (software); Search engine indexing; Context (archaeology); Document retrieval; Question answering; Natural language; Automatic indexing","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":[0.002168745,0.0008337946,0.000725836,0.001438482,0.001501485,0.00295881,0.001948292,0.002089945,0.0296308],"category_scores_gemma":[0.00599913,0.0003716091,0.0003516118,0.001234281,0.0004717714,0.004611045,0.002693575,0.001441465,0.01246941],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008962294,"about_ca_system_score_gemma":0.0009432916,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001372225,"about_ca_topic_score_gemma":0.003124502,"domain_scores_codex":[0.9987056,0.0008014617,0.00005531852,0.0001383976,0.0002064335,0.00009267724],"domain_scores_gemma":[0.9930028,0.00560127,0.0001231355,0.0003062668,0.0003620542,0.0006044418],"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":[0.0008889314,0.001544665,0.001900821,0.00121172,0.00005128886,0.0007047502,0.006956212,0.003660025,0.03047846,0.01612347,0.1260064,0.8104733],"study_design_scores_gemma":[0.000562722,0.002462469,0.009145561,0.0008435173,0.000234241,0.002582418,0.009461025,0.212294,0.04731177,0.04584649,0.6688774,0.000378402],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.149717,0.004522028,0.6238745,0.005544934,0.001444818,0.001030675,0.001787709,0.05979123,0.1522871],"genre_scores_gemma":[0.4066862,0.001521617,0.3812926,0.00234083,0.0009585043,0.001270167,0.002805431,0.004332764,0.1987918],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0296308,"threshold_uncertainty_score":0.09912491,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01884956439314391,"score_gpt":0.2897360571952305,"score_spread":0.2708864928020866,"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."}}