activity
20242026
collaborators
Showing cs.CLShow all

7 papers · 1 filter

cs.CL2026

Can Released LLM Vocabularies Support Token-Level Estimation of Hidden Corpora?

Qingjie Zhang, Xingzhang Ren, Zixuan Chen +6

Pretraining corpus composition shapes LLM capabilities, but it often remains hidden even when model weights are released. Prior work has inferred corpus mixtures or traced specific…

cs.CL2026

Auditing Chinese Web-scale Corpora via Sampled BPE Token Statistics

Qingjie Zhang, Ziqi Tang, Jie Zhang +7

Chinese web pollution has surfaced in LLMs, motivating audits of upstream Chinese corpora. However, auditing such corpora faces three challenges: (1) their web-scale size makes ful…

cs.CL2025

When Audio and Text Disagree: Revealing Text Bias in Large Audio-Language Models

Cheng Wang, Gelei Deng, Xianglin Yang +2

Large Audio-Language Models (LALMs) are enhanced with audio perception capabilities, enabling them to effectively process and understand multimodal inputs that combine audio and te…

cs.CL2025

Understanding the Dark Side of LLMs' Intrinsic Self-Correction

Qingjie Zhang, Di Wang, Haoting Qian +7

Intrinsic self-correction was proposed to improve LLMs' responses via feedback prompts solely based on their inherent capability. However, recent works show that LLMs' intrinsic se…

cs.CL2024

Course-Correction: Safety Alignment Using Synthetic Preferences

Rongwu Xu, Yishuo Cai, Zhenhong Zhou +6

The risk of harmful content generated by large language models (LLMs) becomes a critical concern. This paper presents a systematic study on assessing and improving LLMs' capability…

cs.CL2024

Walking in Others' Shoes: How Perspective-Taking Guides Large Language Models in Reducing Toxicity and Bias

Rongwu Xu, Zi'an Zhou, Tianwei Zhang +5

The common toxicity and societal bias in contents generated by large language models (LLMs) necessitate strategies to reduce harm. Present solutions often demand white-box access t…