6 papers
Understanding New-Knowledge-Induced Factual Hallucinations in LLMs: Analysis and Interpretation
Renfei Dang, Peng Hu, Zhejian Lai +3
Prior works have shown that fine-tuning on new knowledge can induce factual hallucinations in large language models (LLMs), leading to incorrect outputs when evaluated on previousl…
ExpLang: Improved Exploration and Exploitation in LLM Reasoning with On-Policy Thinking Language Selection
Changjiang Gao, Zixian Huang, Kaichen Yang +3
Current large reasoning models (LRMs) have shown strong ability on challenging tasks after reinforcement learning (RL) based post-training. However, previous work mainly focuses on…
Understanding LLMs' Cross-Lingual Context Retrieval: How Good It Is And Where It Comes From
Changjiang Gao, Hankun Lin, Xin Huang +5
Cross-lingual context retrieval (extracting contextual information in one language based on requests in another) is a fundamental aspect of cross-lingual alignment, but the perform…
LLaMAX2: Your Translation-Enhanced Model also Performs Well in Reasoning
Changjiang Gao, Zixian Huang, Jingyang Gong +3
General Large Language Models (LLMs) excel in reasoning, but those enhanced for translation struggle with reasoning tasks. To address this, we propose a novel translationenhanced r…
Could Thinking Multilingually Empower LLM Reasoning?
Changjiang Gao, Xu Huang, Wenhao Zhu +3
Previous work indicates that large language models exhibit a significant "English bias", i.e. they often perform better when tasks are presented in English. Interestingly, we have…
Large Language Models Are Cross-Lingual Knowledge-Free Reasoners
Peng Hu, Sizhe Liu, Changjiang Gao +5
Large Language Models have demonstrated impressive reasoning capabilities across multiple languages. However, the relationship between capabilities in different languages is less e…