{"id":"W4394782008","doi":"10.1145/3613904.3642934","title":"Unraveling the Dilemma of AI Errors: Exploring the Effectiveness of Human and Machine Explanations for Large Language Models","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; University of Waterloo","keywords":"Dilemma; Computer science; Artificial intelligence; Natural language processing; Human–machine system; Cognitive science; Machine learning; Epistemology; Psychology; Philosophy","routes":{"ca_aff":true,"ca_fund":true,"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":[0.002496618,0.0002039169,0.0003036799,0.0001628924,0.0002241629,0.0001608262,0.001191427,0.00007491501,0.000005000502],"category_scores_gemma":[0.0001380182,0.0001205817,0.0001471444,0.0002577062,0.00007651305,0.0002499894,0.002033056,0.0004294884,0.000001738973],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003539155,"about_ca_system_score_gemma":0.00008568555,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001714541,"about_ca_topic_score_gemma":0.0006077513,"domain_scores_codex":[0.9983805,0.0002491042,0.0004149735,0.0004484148,0.000262156,0.0002447964],"domain_scores_gemma":[0.9974342,0.001287216,0.0001403741,0.0008854289,0.0002193836,0.00003340107],"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":[0.000009440129,0.00003867895,0.00002794681,0.0006876977,0.0000699795,0.000002129053,0.009415229,0.01862338,0.002381275,0.9672629,0.00001646362,0.001464913],"study_design_scores_gemma":[0.00007783267,0.00005639575,0.0001126877,0.0004872169,0.00004385447,0.000002182878,0.001986566,0.5334286,0.1035668,0.3600267,0.00003970778,0.0001715212],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2063855,0.0005946191,0.7903651,0.0005446076,0.0003666996,0.0009681662,0.00007029673,0.00008153728,0.0006234891],"genre_scores_gemma":[0.9967079,0.00002339887,0.002623344,0.0000391388,0.00005312532,0.000457109,0.0000132387,0.00002051577,0.0000622517],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7903224,"threshold_uncertainty_score":0.4917178,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08759386332772177,"score_gpt":0.3359635388024949,"score_spread":0.2483696754747731,"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."}}