{"id":"W4392223779","doi":"10.24963/ijcai.2024/26","title":"Navigating Social Dilemmas with LLM-based Agents via Consideration of Future Consequences","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Game Theory and Voting Systems","field":"Economics, Econometrics and Finance","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Engineering and Physical Sciences Research Council; University of Oxford; Good Ventures Foundation","keywords":"Delegation; Control (management); Business; Computer security; Computer science; Political science; Artificial intelligence; Law","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":[0.0008199243,0.000258298,0.0006651232,0.00008340755,0.0001296178,0.0001425012,0.0001852451,0.0003219052,0.0004844492],"category_scores_gemma":[0.00003620299,0.0002438279,0.0001697676,0.0001295341,0.0002220895,0.00004433835,0.00009616132,0.0006892469,0.0001396648],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005597521,"about_ca_system_score_gemma":0.0000897554,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006072802,"about_ca_topic_score_gemma":0.00006637611,"domain_scores_codex":[0.998289,0.00006046865,0.0008548983,0.000532071,0.00006242047,0.000201079],"domain_scores_gemma":[0.9986993,0.00007643479,0.0008660677,0.0002496626,0.00006695119,0.00004159635],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00007085475,0.0001388538,0.01213922,0.003228919,0.0006235795,0.00002752241,0.005695656,0.002800912,0.0001515854,0.9729487,0.001020967,0.001153285],"study_design_scores_gemma":[0.002103867,0.0005631332,0.003518886,0.003546635,0.000282245,0.00004521119,0.003280136,0.05758828,0.007968106,0.9100257,0.008479357,0.00259844],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9681918,0.001447177,0.005045922,0.002609709,0.002343406,0.000663785,0.0007099775,0.0001730332,0.01881517],"genre_scores_gemma":[0.9978734,0.000005594408,0.0009323623,0.0001613982,0.0005300231,0.00004272884,0.00009487663,0.00003459396,0.0003250017],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.06292295,"threshold_uncertainty_score":0.9943013,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05002284425876859,"score_gpt":0.2756504319227501,"score_spread":0.2256275876639816,"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."}}