{"id":"W4412889420","doi":"10.18653/v1/2025.acl-short.97","title":"Counterfactual-Consistency Prompting for Relative Temporal Understanding in Large Language Models","year":2025,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Institute for Information and Communications Technology Promotion; Ministry of Science and ICT, South Korea; National Research Foundation of Korea; Seoul National University; National Research Foundation","keywords":"Counterfactual thinking; Computer science; Consistency (knowledge bases); Artificial intelligence; Natural language processing; Psychology; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01340257,0.001470847,0.001248546,0.001736572,0.001179667,0.003324069,0.00316974,0.002333901,0.006362199],"category_scores_gemma":[0.07180468,0.0009183825,0.001897976,0.001330546,0.001695772,0.009394937,0.0057285,0.005400657,0.001368796],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001768769,"about_ca_system_score_gemma":0.003514019,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002738926,"about_ca_topic_score_gemma":0.005766189,"domain_scores_codex":[0.9907736,0.005512655,0.0005364817,0.001849986,0.001109028,0.0002182361],"domain_scores_gemma":[0.9435791,0.0435303,0.003131064,0.007221753,0.001785373,0.0007524363],"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":[0.001566501,0.00051713,0.009742863,0.001545792,0.000388271,0.001077643,0.007563139,0.1710743,0.01789735,0.2440217,0.02191935,0.5226859],"study_design_scores_gemma":[0.0001083861,0.00006216446,0.0004002911,0.00009395716,0.00007708896,0.0001943519,0.0003581822,0.7707428,0.00605437,0.2108398,0.01101081,0.00005769833],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01110885,0.0002644758,0.980873,0.0008076747,0.00006986663,0.0001473778,0.0005693363,0.005216441,0.0009428259],"genre_scores_gemma":[0.3009243,0.0001815297,0.6941051,0.0005455541,0.0001632277,0.000303244,0.002016122,0.0008272693,0.000933593],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01340257,"threshold_uncertainty_score":0.07088041,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0692207462450151,"score_gpt":0.3069790829925247,"score_spread":0.2377583367475096,"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."}}