{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004850022,0.00009837831,0.0001485044,0.0001623547,0.0001052309,0.00008649177,0.0003100787,0.00005600042,0.000005537233],"category_scores_gemma":[0.00005639374,0.00009072474,0.00004434169,0.0002337584,0.00001254433,0.0006833936,0.0001649675,0.0001121476,0.000002035954],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002210055,"about_ca_system_score_gemma":0.0001067272,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008236884,"about_ca_topic_score_gemma":0.0002566996,"domain_scores_codex":[0.9989815,0.00002950108,0.0002585657,0.0003394774,0.0001087247,0.0002822166],"domain_scores_gemma":[0.9994414,0.0001710717,0.00004944356,0.0002826029,0.00002985231,0.00002564109],"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":[0.000003818606,0.00002201768,0.0007676857,0.00002764512,0.000009678065,0.000003471797,0.004076447,0.001136754,0.00005790594,0.9930832,0.00006442,0.0007469555],"study_design_scores_gemma":[0.0004936919,0.00001237517,0.00003443982,0.00007624329,0.000002417599,7.735025e-7,0.001925175,0.8412125,0.0001560487,0.1559438,0.00004930815,0.00009320259],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01342268,0.0001061752,0.9584308,0.00077507,0.0001463658,0.0003520638,0.000002419301,0.0001247328,0.0266397],"genre_scores_gemma":[0.8955107,9.655452e-7,0.1027302,0.0002624633,0.00001035056,0.00002442519,0.00000155701,0.000004478263,0.001454848],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8820881,"threshold_uncertainty_score":0.3699647,"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."}}