{"id":"W4411446549","doi":"10.1109/jstsp.2025.3581484","title":"Split Fine-Tuning for Large Language Models in Wireless Networks","year":2025,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Signal Processing","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Basic and Applied Basic Research Foundation of Guangdong Province; National Natural Science Foundation of China","keywords":"Computer science; Wireless; Wireless network; Computer network; Artificial intelligence; Telecommunications","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":[0.002686595,0.001553409,0.001829028,0.0009864353,0.0009537925,0.001672219,0.00285898,0.001577512,0.003162374],"category_scores_gemma":[0.01228334,0.001157666,0.001352619,0.001043053,0.001115794,0.004299951,0.002855134,0.003053563,0.001770581],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001443959,"about_ca_system_score_gemma":0.00157613,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009470819,"about_ca_topic_score_gemma":0.01488715,"domain_scores_codex":[0.9977804,0.0006804185,0.0001708888,0.0007674243,0.0003129895,0.0002879347],"domain_scores_gemma":[0.994545,0.003951181,0.0002442807,0.0007173169,0.0003761679,0.000166094],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005982548,0.0002325374,0.001701931,0.00022702,0.0001755569,0.0004272508,0.0002748211,0.6651827,0.01399045,0.006979066,0.00770673,0.3025037],"study_design_scores_gemma":[0.00001864286,0.00002054667,0.00009373322,0.000003940655,0.00001089025,0.00002758386,0.00002068647,0.9919539,0.001897539,0.005389871,0.0005532589,0.000009369259],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02899358,0.0006321462,0.961239,0.0004113179,0.00008756704,0.0001009187,0.0002868306,0.00723112,0.001017469],"genre_scores_gemma":[0.6302049,0.0005282813,0.358213,0.0008911832,0.0002035494,0.0004905232,0.00179277,0.001401011,0.006274838],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009470819,"threshold_uncertainty_score":0.01883137,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01948611781596546,"score_gpt":0.2893391874151269,"score_spread":0.2698530695991614,"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."}}