activity
20242026
collaborators

9 papers

cs.CL2026

Preference Heads in Large Language Models: A Mechanistic Framework for Interpretable Personalization

Weixu Zhang, Ye Yuan, Changjiang Han +7

Large Language Models (LLMs) exhibit strong implicit personalization ability, yet most existing approaches treat this behavior as a black box, relying on prompt engineering or fine…

cs.CL2026

Context-Fidelity Boosting: Enhancing Faithful Generation through Watermark-Inspired Decoding

Weixu Zhang, Fanghua Ye, Qiang Gao +7

Large language models (LLMs) often produce content that contradicts or overlooks information provided in the input context, a phenomenon known as faithfulness hallucination. In thi…

cs.AI2026

LLM Safety From Within: Detecting Harmful Content with Internal Representations

Difan Jiao, Yilun Liu, Ye Yuan +4

Guard models are widely used to detect harmful content in user prompts and LLM responses. However, state-of-the-art guard models rely solely on terminal-layer representations and o…

cs.IR2026

Give Users the Wheel: Towards Promptable Recommendation Paradigm

Fuyuan Lyu, Chenglin Luo, Qiyuan Zhang +6

Conventional sequential recommendation models have achieved remarkable success in mining implicit behavioral patterns. However, these architectures remain structurally blind to exp…

cs.CL2026

Optimizing User Profiles via Contextual Bandits for Retrieval-Augmented LLM Personalization

Linfeng Du, Ye Yuan, Zichen Zhao +8

Large language models (LLMs) excel at general-purpose tasks, yet adapting their responses to individual users remains challenging. Retrieval augmentation provides a lightweight alt…

cs.IR2025

Audio Prototypical Network For Controllable Music Recommendation

Fırat Öncel, Emiliano Penaloza, Haolun Wu +4

Traditional recommendation systems represent user preferences in dense representations obtained through black-box encoder models. While these models often provide strong recommenda…