{"id":"W4400267753","doi":"10.1145/3649217.3653554","title":"Can Small Language Models With Retrieval-Augmented Generation Replace Large Language Models When Learning Computer Science?","year":2024,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Universitas Brawijaya","keywords":"Computer science; Language model; Natural language processing; Artificial intelligence; Universal Networking Language; Information retrieval; Natural language; Comprehension approach","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":[0.009797305,0.001226914,0.00129087,0.001066319,0.0007806824,0.003493999,0.003265655,0.002578572,0.008013146],"category_scores_gemma":[0.04942959,0.001080293,0.001898836,0.0009653681,0.001903038,0.01615334,0.002779438,0.00386673,0.007921291],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001215357,"about_ca_system_score_gemma":0.002632041,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0102353,"about_ca_topic_score_gemma":0.01186816,"domain_scores_codex":[0.9939013,0.003850239,0.000256631,0.0009713951,0.0006622836,0.0003582241],"domain_scores_gemma":[0.9743966,0.01585255,0.0006339857,0.007062989,0.001658289,0.0003956039],"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":[0.001738873,0.0006405884,0.006607118,0.0008820629,0.0003974969,0.0004078962,0.002054264,0.08571647,0.01041232,0.09152561,0.04324065,0.7563766],"study_design_scores_gemma":[0.0002687241,0.0002999613,0.0007977667,0.0001989013,0.0001924454,0.000401162,0.0004557614,0.7286003,0.008508846,0.2212523,0.03888708,0.0001367421],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03193166,0.002107463,0.9300785,0.01021513,0.001224667,0.0002613504,0.0008556867,0.01283782,0.01048772],"genre_scores_gemma":[0.4616739,0.001392757,0.517149,0.003962363,0.000583708,0.0004014206,0.002309406,0.003081571,0.009445773],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0102353,"threshold_uncertainty_score":0.05181372,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02659316822516559,"score_gpt":0.2482295856993994,"score_spread":0.2216364174742338,"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."}}