6 papers
Chronos: Learning Temporal Dynamics of Reasoning Chains for Test-Time Scaling
Kai Zhang, Jiayi Liao, Chengpeng Li +3
Test-Time Scaling (TTS) has emerged as an effective paradigm for improving the reasoning performance of large language models (LLMs). However, existing methods -- most notably majo…
Interpretable Reward Model via Sparse Autoencoder
Shuyi Zhang, Wei Shi, Sihang Li +3
Large language models (LLMs) have been widely deployed across numerous fields. Reinforcement Learning from Human Feedback (RLHF) leverages reward models (RMs) as proxies for human…
Multi-Grained Patch Training for Efficient LLM-based Recommendation
Jiayi Liao, Ruobing Xie, Sihang Li +4
Large Language Models (LLMs) have emerged as a new paradigm for recommendation by converting interacted item history into language modeling. However, constrained by the limited con…
More Expressive Attention with Negative Weights
Ang Lv, Ruobing Xie, Shuaipeng Li +5
We propose a novel attention mechanism, named Cog Attention, that enables attention weights to be negative for enhanced expressiveness, which stems from two key factors: (1) Cog At…
RosePO: Aligning LLM-based Recommenders with Human Values
Jiayi Liao, Xiangnan He, Ruobing Xie +5
Recently, there has been a growing interest in leveraging Large Language Models (LLMs) for recommendation systems, which usually adapt a pre-trained LLM to the recommendation scena…
LLaRA: Large Language-Recommendation Assistant
Jiayi Liao, Sihang Li, Zhengyi Yang +4
Sequential recommendation aims to predict users' next interaction with items based on their past engagement sequence. Recently, the advent of Large Language Models (LLMs) has spark…