{"id":"W4385572252","doi":"10.18653/v1/2023.acl-short.133","title":"LI-RAGE: Late Interaction Retrieval Augmented Generation with Explicit Signals for Open-Domain Table Question Answering","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Security token; Relevance (law); Table (database); Domain (mathematical analysis); Representation (politics); Filter (signal processing); Information retrieval; Set (abstract data type); Inference; Labrador Retriever; Data mining; Artificial intelligence; Theoretical computer science; Computer vision; Programming language; Mathematics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006156868,0.0001085861,0.0001195797,0.0001139453,0.0001733899,0.0005017332,0.0004074295,0.00004514584,0.00004015363],"category_scores_gemma":[0.00004166057,0.00009521706,0.00002128267,0.0004946107,0.000003908114,0.001506716,0.0002073472,0.00007422582,0.00003603712],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008555478,"about_ca_system_score_gemma":0.00005249403,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001092345,"about_ca_topic_score_gemma":0.00005050941,"domain_scores_codex":[0.9989048,0.00005014231,0.0002194562,0.0004081015,0.0001876709,0.0002298271],"domain_scores_gemma":[0.9993748,0.00006012605,0.00008775993,0.0003106432,0.0001141758,0.00005247239],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002125037,0.00009836059,0.0001640823,0.00007736633,0.00007245399,0.0000268706,0.001834134,0.3518264,0.5511467,0.05871506,0.00757139,0.02825469],"study_design_scores_gemma":[0.000457067,0.0001220297,0.00004192934,0.00005074949,0.000003497369,0.000005765015,0.00005644244,0.9400759,0.05666187,0.00109931,0.001291706,0.0001336646],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1220908,0.00000689024,0.875453,0.000827333,0.0002980473,0.0005143922,0.000003019456,0.000300527,0.0005059869],"genre_scores_gemma":[0.842239,0.00000740603,0.1522741,0.0003157686,0.0002064732,0.0001368208,0.00009616901,0.00002121761,0.004703089],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7231789,"threshold_uncertainty_score":0.4838225,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06102899969721623,"score_gpt":0.3158652028916367,"score_spread":0.2548362031944205,"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."}}