Haoting Qian — accepted AI-conference papers

2025

Speculating LLMs’ Chinese Training Data Pollution from Their Tokens

Qingjie Zhang, Di Wang, Haoting Qian, Liu Yan, Tianwei Zhang, Ke Xu +4

EMNLP 2025

Tokens are basic elements in the datasets for LLM training. It is well-known that many tokens representing Chinese phrases in the vocabulary of GPT (4o/4o-mini/o1/o3/4.5/4.1/o4-mini) are indicating contents like pornography or online gambling. Based on this observation, our goal is to locate Pollute

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2025

Understanding the Dark Side of LLMs’ Intrinsic Self-Correction

Qingjie Zhang, Di Wang, Haoting Qian, Yiming Li, Tianwei Zhang, Minlie Huang +4

ACL 2025long

Intrinsic self-correction was initially proposed to improve LLMs’ responses via feedback solely based on their inherent capability. However, recent works show that LLMs’ intrinsic self-correction fails without oracle labels as feedback. In this paper, our research goal is to *interpret LLMs’ intrins…

Cited by 0 Source ↗PDF ↗Scholar ↗