2 papers
cs.CL2026
Mitigating Selection Bias in Large Language Models via Permutation-Aware GRPO
Jinquan Zheng, Jia Yuan, Jiacheng Yao +3
Large language models (LLMs) used for multiple-choice and pairwise evaluation tasks often exhibit selection bias due to non-semantic factors like option positions and label symbols…
cs.CL2025
Chain-of-Thought Prompting Obscures Hallucination Cues in Large Language Models: An Empirical Evaluation
Jiahao Cheng, Tiancheng Su, Jia Yuan +5
Large Language Models (LLMs) often exhibit \textit{hallucinations}, generating factually incorrect or semantically irrelevant content in response to prompts. Chain-of-Thought (CoT)…