{"id":"W4401312022","doi":"10.18260/1-2--48541","title":"Work-in-Progress: Fine-Tuning Large Language Models for Automated Feedback in Complex Engineering Problem-Solving","year":2024,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"3v Geomatics (Canada); Queen's University; University of Alberta","funders":"Queen's University","keywords":"Computer science; Process (computing); Domain (mathematical analysis); Work in process; Fine-tuning; Artificial intelligence; Quality (philosophy); Diversity (politics); Engineering; Programming language","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001977257,0.0002543809,0.0003336521,0.0003362645,0.00007936009,0.0005708448,0.0005031432,0.00009193894,0.0007733239],"category_scores_gemma":[0.0001522296,0.0002237088,0.00005424122,0.0007680636,0.00004853422,0.0005945835,0.0002298148,0.0001895814,0.0001128429],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001222902,"about_ca_system_score_gemma":0.00005812063,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001777417,"about_ca_topic_score_gemma":0.0001377125,"domain_scores_codex":[0.9976419,0.00008595701,0.0005214753,0.0006290016,0.0002840039,0.0008377063],"domain_scores_gemma":[0.9993373,0.0002025737,0.00006419672,0.000283287,0.0000341407,0.00007853704],"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":[0.00003728216,0.00006082271,0.0007950761,0.0006770315,0.000004632171,0.00008155878,0.00385229,0.4567871,0.530959,0.004958207,0.001103251,0.0006837789],"study_design_scores_gemma":[0.000369908,0.00002767546,0.001904249,0.0005349452,0.000003982514,0.000007671897,0.0001516566,0.9920195,0.004055975,0.0002171228,0.000415262,0.0002920885],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9372783,0.0006101807,0.05629465,0.0005764261,0.0006269598,0.0008790587,0.00003678047,0.002703768,0.0009938705],"genre_scores_gemma":[0.8207362,0.000002104738,0.1787006,0.00004542571,0.00008137657,0.0001117063,0.00002219244,0.0000460809,0.0002543621],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5352324,"threshold_uncertainty_score":0.912258,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01765739101056635,"score_gpt":0.2900544829488644,"score_spread":0.2723970919382981,"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."}}