Papers by Peilin Zhao
Curriculum-RLAIF: Curriculum Alignment with Reinforcement Learning from AI Feedback (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to align large language models with human preferences are limited in generalizability due to distribution shift, preference label noise, and mismatch of challenging samples with model capacity. |
| Approach: | They propose a framework that constructs preference pairs with varying difficulty levels and then produces a specific curriculum for reward model training. |
| Outcome: | The proposed framework improves generalizability of reward models by a significant margin without incurring additional inference costs compared to existing non-curriculum baselines. |
LLM-Based Agent Society Investigation: Collaboration and Confrontation in Avalon Gameplay (2024.emnlp-main)
Copied to clipboard
Yihuai Lan, Zhiqiang Hu, Lei Wang, Yang Wang, Deheng Ye, Peilin Zhao, Ee-Peng Lim, Hui Xiong, Hao Wang
| Challenge: | Existing studies on LLM agents' social behaviors are lacking . previous studies focused on positive social behaviors, leaving research on negative social behaviors relatively scarce. |
| Approach: | They propose a framework that features a multi-agent system facilitating efficient communication and interaction with LLM agents. |
| Outcome: | The proposed framework is based on Avalon and evaluates on game success and analyzes agents’ social behaviors. |
WatME: Towards Lossless Watermarking Through Lexical Redundancy (2024.acl-long)
Copied to clipboard
| Challenge: | Existing methods for text watermarking rely on arbitrary vocabulary partitioning during decoding, which compromises the availability of suitable tokens and significantly degrades the quality of responses. |
| Approach: | They propose a method that leverages linguistic prior knowledge of lexical redundancies in LLM vocabularies to seamlessly integrate watermarks. |
| Outcome: | The proposed approach preserves the expressive power of large language models while preserving watermark detectability. |
AEGIS: A Holistic Benchmark for Evaluating Forensic Analysis of AI-Generated Academic Images (2026.acl-long)
Copied to clipboard
Bo Zhang, Tzu-Yen Ma, Zichen Tang, Junpeng Ding, Zirui Wang, Yizhuo Zhao, Peilin Gao, Zijie Xi, Zixin Ding, Haiyang Sun, Haocheng Gao, Yuan Liu, Liangjia Wang, Yiling Huang, Yujie Wang, Yuyue Zhang, Ronghui Xi, Yuanze Li, Jiacheng Liu, Zhongjun Yang, Haihong E
| Challenge: | AEGIS examines whether current models can effectively audit AI-generated images in academic papers. |
| Approach: | They propose a holistic benchmark for forensic analysis of AI-Generated academic ImageS that reveals limitations in academic image forensics. |
| Outcome: | AEGIS compared with existing benchmarks on seven academic categories and features key advances in forensic analysis. |
The Stackelberg Speaker: Optimizing Persuasive Communication in Social Deduction Games (2026.acl-long)
Copied to clipboard
| Challenge: | Existing approaches focus on information processing and strategy selection, overlooking the significance of persuasive communication in social deduction games. |
| Approach: | They propose a reinforcement learning framework that trains agents to optimize influential utterances for persuasive impact by formalizing turn-based dialogue as a Stackelberg competition . |
| Outcome: | The proposed framework outperforms baselines across four social deduction benchmarks and shows that it is effective in persuasive communication. |