paper-with-me

홈 › Papers

How reliable are LLMs when it comes to playing dice?

2026-06-05 · Luca Avena, Gianmarco Bet, Bernardo Busoni arxiv

We investigate the probabilistic reasoning capabilities of large language models through a controlled benchmarking study on discrete probability problems. We constructed two datasets, respectively a set of standard exercises and a set of counterintuitive exercises, designed to trigger heuristic reasoning, and evaluated 8 state-of-the-art models, each tested with and without Chain-of-Thought prompting. Models achieve an average accuracy of 0.96 on standard problems but only 0.59 on counterintuitive ones. We further provide empirical evidence of token bias: performance drops by over 20% when canonical formulations are replaced by disguised variants. Embedding misleading suggestions in the prompt reduces performance by up to 34%, with no model proving immune. Taken together, the reported findings suggest that current LLMs are not yet genuine probabilistic reasoners, despite their success in advanced mathematical problems.

📄 PDF Abstract BibTeX arXiv:2606.07515

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Do Role-Playing Agents Practice What They Preach? Belief-Behavior Consistency in LLM-Based Simulations of Human Trust

2025-07-02 · Amogh Mannekote, Adam Davies, Guohao Li, Kristy Elizabeth Boyer 외 arxiv

As LLMs are increasingly studied as role-playing agents to generate synthetic data for human behavioral research, ensuring that their outputs remain coherent with their assigned roles has become a critical concern. In th…

Revealing and Mitigating the Challenge of Detecting Character Knowledge Errors in LLM Role-Playing

2024-09-18 · Wenyuan Zhang, Shuaiyi Nie, Jiawei Sheng, Zefeng Zhang 외

Large language model (LLM) role-playing has gained widespread attention. Authentic character knowledge is crucial for constructing realistic LLM role-playing agents. However, existing works usually overlook the explorati…

Language ModelingLanguage ModellingLarge Language Model

Persona is a Double-edged Sword: Mitigating the Negative Impact of Role-playing Prompts in Zero-shot Reasoning Tasks

2024-08-16 · Junseok Kim, Nakyeong Yang, Kyomin Jung

Recent studies demonstrate that prompting a role-playing persona to an LLM improves reasoning capability. However, assigning an adequate persona is difficult since LLMs are extremely sensitive to assigned prompts; thus, …

Position

Playing games with Large language models: Randomness and strategy

2025-03-04 · Alicia Vidler, Toby Walsh

Playing games has a long history of describing intricate interactions in simplified forms. In this paper we explore if large language models (LLMs) can play games, investigating their capabilities for randomisation and s…

PokerBench: Training Large Language Models to become Professional Poker Players

2025-01-14 · Richard Zhuang, Akshat Gupta, Richard Yang, Aniket Rahane 외

We introduce PokerBench - a benchmark for evaluating the poker-playing abilities of large language models (LLMs). As LLMs excel in traditional NLP tasks, their application to complex, strategic games like poker poses a n…