{"id":"W4389519982","doi":"10.18653/v1/2023.findings-emnlp.97","title":"On the Risk of Misinformation Pollution with Large Language Models","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":60,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Ministry of Education - Singapore; Bộ Giáo dục và Ðào tạo; Ministry of Education, India; National Science Foundation","keywords":"Misinformation; Obstacle; Harm; Computer science; Internet privacy; Risk analysis (engineering); Computer security; Data science; Psychology; Political science; Business; Social psychology","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":[0.0003010623,0.00003489727,0.00003677473,0.0000475511,0.00005157002,0.00002118685,0.000207549,0.00001443305,0.00000827093],"category_scores_gemma":[0.00001653058,0.00001829163,0.00001549888,0.0002338871,0.000005685983,0.0002527141,0.00004890709,0.00004310693,0.00003933352],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008028842,"about_ca_system_score_gemma":0.00001282332,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000663379,"about_ca_topic_score_gemma":0.00001812482,"domain_scores_codex":[0.9995733,0.00002129864,0.00007978157,0.00006796216,0.000167199,0.00009040585],"domain_scores_gemma":[0.9995841,0.00004300736,0.00004488938,0.0002957974,0.00002025066,0.00001190506],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002684714,0.000007222815,0.00003236192,0.000003902037,0.000005911901,5.387965e-7,0.003932704,0.1093993,0.00005414765,0.8805416,0.0005452085,0.005474427],"study_design_scores_gemma":[0.00009252825,0.00001839695,0.0003864123,0.000006916456,0.000001311956,4.954744e-7,0.0002842134,0.9894596,0.0008036065,0.008893889,0.0000250211,0.00002758399],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2443059,0.000003156213,0.74769,0.0005924993,0.00002261036,0.00005564218,0.000001859628,0.00009640463,0.007231861],"genre_scores_gemma":[0.9942854,0.000003175255,0.005156107,0.0002074737,0.000007270104,0.000002493598,0.000001151486,0.000001624169,0.0003352724],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8800604,"threshold_uncertainty_score":0.07459109,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01591063612662517,"score_gpt":0.2270961714336405,"score_spread":0.2111855353070153,"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."}}