5 papers
HeadEdit: Calibrating Language Model Behavior Through the Frozen Unembedding Matrix
Zirui He, Haiyan Zhao, Jingyu Hu +5
Alignment does not eliminate behavioral errors in language models. Models may still refuse benign requests, call unnecessary tools, or yield to false user claims. Current methods m…
Fine-Grained Interpretation of Political Opinions in Large Language Models
Jingyu Hu, Mengyue Yang, Mengnan Du +1
Studies of LLMs' political opinions mainly rely on evaluations of their open-ended responses. Recent work indicates that there is a misalignment between LLMs' responses and their i…
Large Vision-Language Model Alignment and Misalignment: A Survey Through the Lens of Explainability
Dong Shu, Haiyan Zhao, Jingyu Hu +4
Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities in processing both visual and textual information. However, the critical challenge of alignment betwe…
ProxiMix: Enhancing Fairness with Proximity Samples in Subgroups
Jingyu Hu, Jun Hong, Mengnan Du +1
Many bias mitigation methods have been developed for addressing fairness issues in machine learning. We found that using linear mixup alone, a data augmentation technique, for bias…
Strategic Demonstration Selection for Improved Fairness in LLM In-Context Learning
Jingyu Hu, Weiru Liu, Mengnan Du
Recent studies highlight the effectiveness of using in-context learning (ICL) to steer large language models (LLMs) in processing tabular data, a challenging task given the structu…