{"id":"W7077856092","doi":"10.48448/d6cr-4k73","title":"A Guide To Effectively Leveraging LLMs for Low-Resource Text Summarization: Data Augmentation and Semi-supervised Approaches","year":2025,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; McGill University","funders":"","keywords":"Automatic summarization; Inference; Quality (philosophy); Measure (data warehouse); Language model; Readability; Labeled data; Codebase","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"],"consensus_categories":[],"category_scores_codex":[0.001186155,0.0002789599,0.000272049,0.0003779544,0.0003612364,0.0004251054,0.002512162,0.0001380313,0.00003745959],"category_scores_gemma":[0.0006540852,0.0002639871,0.00002711186,0.001010111,0.0002425245,0.0003602071,0.001865369,0.0001360041,0.000009223389],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007769756,"about_ca_system_score_gemma":0.0004717747,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001334602,"about_ca_topic_score_gemma":0.00004723672,"domain_scores_codex":[0.9974384,0.00004938553,0.0002728018,0.001423204,0.0003988485,0.0004174107],"domain_scores_gemma":[0.9981693,0.0002198255,0.0001595261,0.001170731,0.0001337914,0.0001468038],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002476601,0.0001921516,0.0004403081,0.001283433,0.0001100861,0.000009813161,0.001416298,0.003833611,0.004347282,0.02547244,0.5571694,0.4057004],"study_design_scores_gemma":[0.0005273111,0.0000497621,0.0000754053,0.0003782296,0.00002420788,0.000006723405,0.0002118724,0.4983009,0.001387801,0.0009935327,0.4976147,0.0004295228],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.00001634053,0.0001173765,0.8094455,0.002827581,0.0001949576,0.0007579726,0.0000530012,0.0001894144,0.1863979],"genre_scores_gemma":[0.008540383,0.00002198307,0.3750526,0.002005651,0.0004460153,0.0001594121,0.0006342677,0.0000545855,0.6130851],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4944673,"threshold_uncertainty_score":0.9999812,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0479054683704552,"score_gpt":0.289259888969461,"score_spread":0.2413544205990058,"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."}}