{"id":"W4403659146","doi":"10.1007/s11227-024-06499-7","title":"Enhancing Chinese comprehension and reasoning for large language models: an efficient LoRA fine-tuning and tree of thoughts framework","year":2024,"lang":"en","type":"article","venue":"The Journal of Supercomputing","topic":"Topic Modeling","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Montréal","funders":"Sichuan Province Science and Technology Support Program","keywords":"Computer science; Comprehension; Tree (set theory); Artificial intelligence; Natural language processing; Theoretical computer science; 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":[0.001576973,0.000895582,0.001345905,0.001490022,0.001039772,0.002036249,0.002445619,0.0008341133,0.008616065],"category_scores_gemma":[0.006508486,0.0005444161,0.002032438,0.001126852,0.000802683,0.004677376,0.002882354,0.002185029,0.002450441],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001211484,"about_ca_system_score_gemma":0.003212852,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008757343,"about_ca_topic_score_gemma":0.01441326,"domain_scores_codex":[0.9987453,0.0003986592,0.0001093074,0.0003235984,0.0002793282,0.0001437521],"domain_scores_gemma":[0.9967218,0.001447477,0.0001137135,0.0008047121,0.0007127628,0.0001994745],"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":[0.0006464237,0.0006154857,0.003100249,0.0004610073,0.0002114152,0.0004984274,0.001597068,0.06002975,0.02734623,0.0673518,0.02395851,0.8141837],"study_design_scores_gemma":[0.00005366978,0.00006642627,0.0002931091,0.00001534649,0.00009613193,0.00007780637,0.0002120182,0.9327101,0.008923966,0.05201417,0.00550502,0.0000322307],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03251089,0.0002460952,0.9470865,0.0004469538,0.00007316477,0.0001816434,0.0004849084,0.0152206,0.003749389],"genre_scores_gemma":[0.3494346,0.0001517121,0.6434933,0.0002351331,0.0000886812,0.0002180597,0.001313899,0.001005425,0.004059264],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008757343,"threshold_uncertainty_score":0.02882361,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01750393598384367,"score_gpt":0.2834888811719226,"score_spread":0.2659849451880789,"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."}}