{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001106047,0.0003176679,0.0002914296,0.0001431361,0.0002597574,0.00139777,0.003377257,0.0001547546,0.00002633889],"category_scores_gemma":[0.002502077,0.0002659875,0.00008478696,0.0006251409,0.00003783749,0.00116193,0.001742609,0.0006127355,0.00003385982],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006460859,"about_ca_system_score_gemma":0.00008712547,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001609691,"about_ca_topic_score_gemma":0.000005948466,"domain_scores_codex":[0.9971735,0.00004941391,0.0005659973,0.001151621,0.0004398119,0.0006196663],"domain_scores_gemma":[0.9970775,0.0009889175,0.00008214969,0.00161837,0.00007446998,0.0001586336],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000004448858,0.00003139543,0.0001003634,0.0002606503,0.00004426127,0.0001054448,0.003939926,0.1015982,0.0006395959,0.672863,0.00006469194,0.220348],"study_design_scores_gemma":[0.00002344289,0.0000465099,0.000037527,0.0004467017,0.00001000195,0.0000722141,0.00004989273,0.9839883,0.0001097163,0.01449052,0.0004102202,0.0003149078],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007559526,0.0009479024,0.9880491,0.0008340873,0.001095698,0.0003753329,0.00002087379,0.001071877,0.00004562119],"genre_scores_gemma":[0.3681177,0.00001030696,0.6310749,0.0002167997,0.0004560454,0.00004028619,0.00004478011,0.00002491692,0.00001428715],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8823901,"threshold_uncertainty_score":0.9999793,"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."}}