{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001736249,0.0001409129,0.0002780214,0.0001405508,0.0002113457,0.0001470463,0.0003733229,0.00005696576,5.981859e-7],"category_scores_gemma":[0.0001219713,0.00009032185,0.0000644232,0.0002110245,0.00002669409,0.0004481744,0.0002863803,0.0003380343,1.299983e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002065967,"about_ca_system_score_gemma":0.00003891844,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001565,"about_ca_topic_score_gemma":0.00001168662,"domain_scores_codex":[0.9987444,0.00012522,0.0004516931,0.0001959986,0.0002457985,0.0002368489],"domain_scores_gemma":[0.9985091,0.0009358753,0.0001327754,0.0002430278,0.00009919679,0.00008002515],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009985616,0.0001460773,0.001075024,0.0008983092,0.0001615628,0.0001027979,0.2755671,0.4022655,0.09213939,0.05460772,0.00001914168,0.1729175],"study_design_scores_gemma":[0.0002299696,0.00009540049,0.0002247654,0.001223577,0.00002496643,0.0002303483,0.00149306,0.9914195,0.001029173,0.003924894,0.000007274419,0.00009707325],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4965181,0.003802624,0.49933,0.00009883708,0.0001672418,0.00005224146,6.45122e-7,0.00002145722,0.000008950868],"genre_scores_gemma":[0.7797329,0.00003194686,0.2198766,0.00003395174,0.00030998,2.848094e-7,3.008394e-7,0.00001171011,0.000002347326],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.589154,"threshold_uncertainty_score":0.3683218,"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."}}