{"id":"W7126396826","doi":"10.21428/594757db.c3f7036d","title":"Rumour Evaluation with Very Large Language Models","year":2024,"lang":"en","type":"article","venue":"","topic":"Misinformation and Its Impacts","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Interpretability; Misinformation; Leverage (statistics); Social media; Task (project management); Scheme (mathematics); Trustworthiness; Language model","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":[0.009950331,0.002366163,0.001531957,0.001707761,0.001231388,0.002616788,0.002090336,0.00270114,0.003822264],"category_scores_gemma":[0.03717058,0.0005040719,0.001540925,0.00109299,0.0009860763,0.004273119,0.002362327,0.003710774,0.002314789],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001597185,"about_ca_system_score_gemma":0.001758956,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01028951,"about_ca_topic_score_gemma":0.009188921,"domain_scores_codex":[0.9925753,0.004696559,0.0005323343,0.001063796,0.0008092417,0.0003228407],"domain_scores_gemma":[0.9700509,0.02477565,0.0006388486,0.00206789,0.001841619,0.0006249755],"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":[0.006453379,0.002815589,0.01841832,0.002401056,0.00132526,0.001589846,0.00188006,0.4453789,0.01121132,0.005942708,0.04332781,0.4592557],"study_design_scores_gemma":[0.0001486001,0.0003274335,0.0009494816,0.00004223054,0.00007334954,0.00009727239,0.0002900707,0.9896709,0.003395436,0.003142473,0.001812625,0.00005015225],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6937537,0.01037448,0.2322559,0.003781807,0.001674817,0.0009703443,0.009770263,0.0349423,0.01247635],"genre_scores_gemma":[0.9172053,0.000577924,0.06890699,0.0004526834,0.0002373569,0.0003187052,0.008828318,0.0004103186,0.003062432],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01028951,"threshold_uncertainty_score":0.05262297,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04164885594460326,"score_gpt":0.3679097320157838,"score_spread":0.3262608760711805,"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."}}