Papers by Yuhang Lai
HAF-RM: A Hybrid Alignment Framework for Reward Model Training (2025.acl-long)
Copied to clipboard
Shujun Liu, Xiaoyu Shen, Yuhang Lai, Siyuan Wang, Shengbin Yue, Zengfeng Huang, Xuanjing Huang, Zhongyu Wei
| Challenge: | Recent studies have focused on enhancing reward models through data improvements, following the conventional training framework for reward models that directly optimizes the predicted rewards. |
| Approach: | They propose a hybrid alignment framework **HAF-RM** that incorporates additional constraint on token-level policy probabilities in addition to the reward score. |
| Outcome: | The proposed framework can supervise the internal preference model at the token level and optimize the mapping layer of the reward model at sequence level. |
ALaRM: Align Language Models via Hierarchical Rewards Modeling (2024.findings-acl)
Copied to clipboard
| Challenge: | Current alignment approaches struggle with inconsistency and sparsity of human supervision signals. |
| Approach: | They propose a framework modeling hierarchical rewards in reinforcement learning from human feedback (RLHF) it integrates holistic rewards with aspect-specific rewards to enhance alignment of large language models with human preferences. |
| Outcome: | The proposed framework improves the alignment of large language models with human preferences by integrating holistic rewards with aspect-specific rewards. |
EvoR: Evolving Retrieval for Code Generation (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing pipelines for retrieval-augmented code generation (RACG) use static knowledge bases with a single source, limiting adaptation capabilities of Large Language Models (LLMs) Extensive experiments demonstrate that EVOR achieves two to four times of execution accuracy compared to other methods such as Reflexion. |
| Approach: | They propose a retrieval-augmented code generation pipeline that employs the synchronous evolution of queries and diverse knowledge bases. |
| Outcome: | The proposed pipeline achieves two to four times of execution accuracy compared to other methods. |
How Jailbreak Defenses Work and Ensemble? A Mechanistic Investigation (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Jailbreak attacks, where harmful prompts bypass generative models’ built-in safety, raise serious concerns about model vulnerability. |
| Approach: | They propose to reframe the standard generation task as a binary classification problem to assess model refusal tendencies for both harmful and benign queries. |
| Outcome: | The proposed defenses improve model safety or optimize the trade-off between safety and helpfulness. |