5 papers
Sentence-Level Contextual Entrainment in Large Language Models
Yang Liu, Chenhui Chu
Contextual entrainment, which is a newly discovered phenomenon in large language models (LLMs), refers to the tendency of a model to assign higher probabilities to tokens that appe…
When and Why Does Unsupervised RL Succeed in Mathematical Reasoning? A Manifold Envelopment Perspective
Zelin Zhang, Fei Cheng, Chenhui Chu
Although outcome-based reinforcement learning (RL) significantly advances the mathematical reasoning capabilities of Large Language Models (LLMs), its reliance on computationally e…
Adaptive Theory of Mind for LLM-based Multi-Agent Coordination
Chunjiang Mu, Ya Zeng, Qiaosheng Zhang +6
Theory of Mind (ToM) refers to the ability to reason about others' mental states, and higher-order ToM involves considering that others also possess their own ToM. Equipping large…
Language Lives in Sparse Dimensions: Toward Interpretable and Efficient Multilingual Control for Large Language Models
Chengzhi Zhong, Fei Cheng, Qianying Liu +3
Large language models exhibit strong multilingual capabilities despite limited exposure to non-English data. Prior studies show that English-centric large language models map multi…
How Does Cognitive Bias Affect Large Language Models? A Case Study on the Anchoring Effect in Price Negotiation Simulations
Yoshiki Takenami, Yin Jou Huang, Yugo Murawaki +1
Cognitive biases, well-studied in humans, can also be observed in LLMs, affecting their reliability in real-world applications. This paper investigates the anchoring effect in LLM-…