activity
20242026
collaborators

7 papers

cs.CL2026

How Controllable Are Large Language Models? A Unified Evaluation across Behavioral Granularities

Ziwen Xu, Kewei Xu, Haoming Xu +8

Large Language Models (LLMs) are increasingly deployed in socially sensitive domains, yet their unpredictable behaviors, ranging from misaligned intent to inconsistent personality,…

cs.CV2026

Seeing but Not Thinking: Routing Distraction in Multimodal Mixture-of-Experts

Haolei Xu, Haiwen Hong, Hongxing Li +7

Multimodal Mixture-of-Experts (MoE) models have achieved remarkable performance on vision-language tasks. However, we identify a puzzling phenomenon termed Seeing but Not Thinking:…

cs.CL2026

Why Steering Works: Toward a Unified View of Language Model Parameter Dynamics

Ziwen Xu, Chenyan Wu, Hengyu Sun +9

Methods for controlling large language models (LLMs), including local weight fine-tuning, LoRA-based adaptation, and activation-based interventions, are often studied in isolation,…

cs.LG2025

Score-based Generative Modeling for Conditional Independence Testing

Yixin Ren, Chenghou Jin, Yewei Xia +6

Determining conditional independence (CI) relationships between random variables is a fundamental yet challenging task in machine learning and statistics, especially in high-dimens…

cs.CL2025

AIR: A Systematic Analysis of Annotations, Instructions, and Response Pairs in Preference Dataset

Bingxiang He, Wenbin Zhang, Jiaxi Song +11

Preference learning is critical for aligning large language models (LLMs) with human values, yet its success hinges on high-quality datasets comprising three core components: Prefe…

cs.IR2025

QExplorer: Large Language Model Based Query Extraction for Toxic Content Exploration

Shaola Ren, Li Ke, Longtao Huang +2

Automatically extracting effective queries is challenging in information retrieval, especially in toxic content exploration, as such content is likely to be disguised. With the rec…