9 papers
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…
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…
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…
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…
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…
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…