{"id":"W4394770144","doi":"10.1162/dint_a_00251","title":"LLaMA-LoRA Neural Prompt Engineering: A Deep Tuning Framework for Automatically Generating Chinese Text Logical Reasoning Thinking Chains","year":2024,"lang":"en","type":"article","venue":"Data Intelligence","topic":"Topic Modeling","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Language model; Artificial intelligence; Natural language processing; Comprehension; Benchmark (surveying); Inference; Logical reasoning; Question answering; Programming language","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":[0.001267313,0.0008533563,0.0006103454,0.0006761675,0.000436985,0.001004045,0.001956587,0.001135747,0.005609137],"category_scores_gemma":[0.004323341,0.0004550172,0.0008995861,0.0004769423,0.0005430565,0.001781789,0.001369663,0.002364241,0.001450158],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001137477,"about_ca_system_score_gemma":0.001719646,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008054056,"about_ca_topic_score_gemma":0.01359953,"domain_scores_codex":[0.999645,0.0001058871,0.00002304041,0.0001227688,0.00005910342,0.00004428639],"domain_scores_gemma":[0.9990811,0.0004278994,0.00006243294,0.0001000566,0.0002515242,0.00007690626],"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":[0.0003179395,0.0004026495,0.002821484,0.0002496094,0.00009719838,0.0002075926,0.0003069866,0.3964435,0.01227521,0.01430817,0.01094352,0.5616261],"study_design_scores_gemma":[0.00001310405,0.00003287789,0.00008988483,0.000007178894,0.000008090213,0.000009098275,0.00001312569,0.9935644,0.001065106,0.00444924,0.0007424815,0.000005320162],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04193411,0.0004320957,0.9411545,0.0006254954,0.0001042359,0.0001912933,0.0005073737,0.01218386,0.002867141],"genre_scores_gemma":[0.5896479,0.0002766679,0.4003469,0.0006659911,0.00008256363,0.0005224294,0.001540276,0.0003928375,0.006524399],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008054056,"threshold_uncertainty_score":0.01876438,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05625293307651095,"score_gpt":0.3232568566701648,"score_spread":0.2670039235936538,"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."}}