{"id":"W7126402336","doi":"10.18653/v1/2024.findings-eacl.43","title":"Capturing the Relationship Between Sentence Triplets for LLM and Human-Generated Texts to Enhance Sentence Embeddings","year":2024,"lang":"","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Institute for Information and Communications Technology Promotion; Ministry of Science and ICT, South Korea; Korea Advanced Institute of Science and Technology","keywords":"Sentence; Feature (linguistics); Semantics (computer science); Term (time)","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":[0.002494284,0.001535892,0.0005736076,0.001163032,0.0004273219,0.0009784801,0.001072641,0.001112102,0.005935248],"category_scores_gemma":[0.01167815,0.0003353867,0.0009527802,0.0009559304,0.0005450135,0.002439677,0.00179699,0.001824441,0.004924945],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006127339,"about_ca_system_score_gemma":0.000603678,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001414171,"about_ca_topic_score_gemma":0.003701799,"domain_scores_codex":[0.9985184,0.00058445,0.00009188469,0.0005576906,0.0001807319,0.00006684569],"domain_scores_gemma":[0.9968165,0.001499361,0.0002508633,0.0008821159,0.000433577,0.0001175966],"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":[0.000815044,0.0005826668,0.01542252,0.001151643,0.0002593592,0.0004601965,0.0009059003,0.05555749,0.07280724,0.007451516,0.05084079,0.7937456],"study_design_scores_gemma":[0.00006281133,0.0005197154,0.006407981,0.000111324,0.0000734119,0.0005607349,0.0003773902,0.9186314,0.04154373,0.01017249,0.02147248,0.00006641916],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1893073,0.001541279,0.7676258,0.0009185699,0.0008602433,0.0005168585,0.008903867,0.02443702,0.005889063],"genre_scores_gemma":[0.4806393,0.0003668345,0.4804675,0.000428213,0.0001759509,0.0007368585,0.02936829,0.001203991,0.00661302],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005935248,"threshold_uncertainty_score":0.01985538,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07427577997439558,"score_gpt":0.3428753693139701,"score_spread":0.2685995893395745,"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."}}