{"total":1,"items":[{"citing_arxiv_id":"2412.11009","ref_index":2,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Dual Traits in Probabilistic Reasoning of Large Language Models","primary_cat":"cs.AI","submitted_at":"2024-12-15T01:33:45+00:00","verdict":"CONDITIONAL","verdict_confidence":"MODERATE","novelty_score":5.0,"formal_verification":"none","one_line_summary":"LLMs flip between correct Bayesian updating and similarity-based representativeness heuristics depending on the structure of the probability question.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"References [1] Arora S, Khandeparkar H, Khodak M, Plevrakis O, Saunshi N (2019) A theoretical analysis of contrastive unsu- pervised representation learning. URL https://arxiv .org/abs/1902.09229. [2] Bar-Hillel M (1980) The base-rate fallacy in probabilit y judgments. Acta Psychologica 44(3):211-233, ISSN 0001-6918, URL http://dx.doi.org/https://doi.org/10.1016/0001-6918(80)90046-3. [3] Binz M, Schulz E (2023) Using cognitive psychology to und erstand gpt-3. Proceedings of the National Academy of Sciences 120(6):e2218523120, URL http://dx.doi.org/10.1073/pnas.2218523120. [4] Cui J, Ning M, Li Z, Chen B, Yan Y , Li H, Ling B, Tian Y , Yuan L ( 2024) Chatlaw: A multi-agent col- laborative legal assistant with knowledge graph enhanced m ixture-of-experts large language model."}],"limit":50,"offset":0}