2 citations · 4 across the 18 of their papers we have counts for
5 papers · 1 filter
Free Process Rewards without Process Labels
Lifan Yuan, Wendi Li, Huayu Chen +6
Different from its counterpart outcome reward models (ORMs), which evaluate the entire responses, a process reward model (PRM) scores a reasoning trajectory step by step, providing…
FATH: Authentication-based Test-time Defense against Indirect Prompt Injection Attacks
Jiongxiao Wang, Fangzhou Wu, Wendi Li +5
Large language models (LLMs) have been widely deployed as the backbone with additional tools and text information for real-world applications. However, integrating external informa…
Process Reward Model with Q-Value Rankings
Wendi Li, Yixuan Li
Process Reward Modeling (PRM) is critical for complex reasoning and decision-making tasks where the accuracy of intermediate steps significantly influences the overall outcome. Exi…
Position Debiasing Fine-Tuning for Causal Perception in Long-Term Dialogue
Shixuan Fan, Wei Wei, Wendi Li +3
The core of the dialogue system is to generate relevant, informative, and human-like responses based on extensive dialogue history. Recently, dialogue generation domain has seen ma…
Reinforcement Learning with Token-level Feedback for Controllable Text Generation
Wendi Li, Wei Wei, Kaihe Xu +3
To meet the requirements of real-world applications, it is essential to control generations of large language models (LLMs). Prior research has tried to introduce reinforcement lea…