7 papers
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,…
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:…
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,…
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…
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…
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…