{"id":"W4412889469","doi":"10.18653/v1/2025.acl-srw.83","title":"DRUM: Learning Demonstration Retriever for Large MUlti-modal Models","year":2025,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Modal; Labrador Retriever; Computer science; Drum; Artificial intelligence; Engineering; Mechanical engineering; Materials science; Medicine","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002998077,0.002940123,0.001960424,0.001100726,0.0006702898,0.001049932,0.004486444,0.002251091,0.008222173],"category_scores_gemma":[0.007773464,0.0008436679,0.00176558,0.0007940942,0.000693238,0.004082715,0.003683365,0.004057628,0.003262756],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00104764,"about_ca_system_score_gemma":0.001158534,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004726193,"about_ca_topic_score_gemma":0.007706903,"domain_scores_codex":[0.99866,0.0003680448,0.00008802306,0.0005154182,0.0002329357,0.0001355625],"domain_scores_gemma":[0.9978369,0.001019063,0.000145867,0.000529215,0.0002968021,0.0001722185],"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":[0.000669602,0.0004755179,0.001857641,0.0005615257,0.0002698741,0.0003229688,0.0002053002,0.1395786,0.01550601,0.005428757,0.02965871,0.8054655],"study_design_scores_gemma":[0.00006126158,0.0002099375,0.0002082932,0.00001404983,0.00002800798,0.00007859342,0.00004127088,0.989235,0.004090387,0.004085866,0.001925601,0.00002175644],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03372114,0.00180361,0.9290599,0.0004450106,0.0001818577,0.0002758976,0.0008900674,0.03182738,0.00179515],"genre_scores_gemma":[0.3698415,0.000772875,0.6125662,0.001093538,0.0002421237,0.0007847713,0.006091997,0.001513372,0.007093689],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008222173,"threshold_uncertainty_score":0.02750587,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0182515041824186,"score_gpt":0.3018993524396694,"score_spread":0.2836478482572508,"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."}}