Papers by Xuewei Wang
How to Build User Simulators to Train RL-based Dialog Systems (D19-1)
Copied to clipboard
| Challenge: | RL-based dialog systems require interaction with the environment and obtaining real human users to interact with the system is time-consuming and labor-intensive. |
| Approach: | They propose a method to standardize user simulator building to compare dialog system quality using the same set of user simulators. |
| Outcome: | The proposed method can be used by the community to compare dialog system quality using the same set of user simulators fairly. |
Self-Generated Critiques Boost Reward Modeling for Language Models (2025.naacl-long)
Copied to clipboard
Yue Yu, Zhengxing Chen, Aston Zhang, Liang Tan, Chenguang Zhu, Richard Yuanzhe Pang, Yundi Qian, Xuewei Wang, Suchin Gururangan, Chao Zhang, Melanie Kambadur, Dhruv Mahajan, Rui Hou
| Challenge: | Existing reward models produce scalar scores and struggle to incorporate critiques in a natural language format. |
| Approach: | They propose a framework that predicts critiques and rewards using self-generated critiques without extra supervision. |
| Outcome: | The proposed framework improves reward modeling accuracy by 3.7%-7.3% compared to standard reward models and LLM judges. |
Persuasion for Good: Towards a Personalized Persuasive Dialogue System for Social Good (P19-1)
Copied to clipboard
| Challenge: | Persuasion agents are a form of communication that can be used to change people's opinions and actions for social good. |
| Approach: | They designed an online persuasion task where one participant was asked to persult the other to donate to a specific charity. |
| Outcome: | The proposed system could change people's opinions and actions for social good. |