9 papers
Representational Equality in Cross-country Value Simulation: A Systematic Analysis of Large Language Models
Xiaowen Jian, Xinyi Mou, Daisong Gong +3
Traditional methods for studying human opinions often struggle to support representative and scalable research across countries. Large language models (LLMs) can serve as scalable…
KARL: Mitigating Hallucinations in LLMs via Knowledge-Boundary-Aware Reinforcement Learning
Cheng Gao, Cheng Huang, Kangyang Luo +5
Enabling large language models (LLMs) to appropriately abstain from answering questions beyond their knowledge is crucial for mitigating hallucinations. While existing reinforcemen…
H-Neurons: On the Existence, Impact, and Origin of Hallucination-Associated Neurons in LLMs
Cheng Gao, Huimin Chen, Chaojun Xiao +3
Large language models (LLMs) frequently generate hallucinations -- plausible but factually incorrect outputs -- undermining their reliability. While prior work has examined halluci…
Large Language Models' Complicit Responses to Illicit Instructions across Socio-Legal Contexts
Xing Wang, Huiyuan Xie, Yiyan Wang +7
Large language models (LLMs) are now deployed at unprecedented scale, assisting millions of users in daily tasks. However, the risk of these models assisting unlawful activities re…
The Overthinker's DIET: Cutting Token Calories with DIfficulty-AwarE Training
Weize Chen, Jiarui Yuan, Tailin Jin +4
Recent large language models (LLMs) exhibit impressive reasoning but often over-think, generating excessively long responses that hinder efficiency. We introduce DIET ( DIfficulty-…
PersLLM: A Personified Training Approach for Large Language Models
Zheni Zeng, Jiayi Chen, Huimin Chen +5
Large language models (LLMs) exhibit human-like intelligence, enabling them to simulate human behavior and support various applications that require both humanized communication an…