Papers by Xuetao Wei
MTA:A Merge-then-Adapt Framework for Personalized Large Language Models (2026.acl-long)
Copied to clipboard
Xiaopeng Li, Yuanjin Zheng, Wanyu Wang, Wenlin Zhang, Pengyue Jia, Yingyi Zhang, Haiying He, Mengyang Ma, Yiqi Wang, Maolin Wang, Xuetao Wei, Xiangyu Zhao
| Challenge: | Personalized Large Language Models (PLLMs) aim to align outputs with individual user preferences . current methods of fine-tuning a separate module for each user are unscalable . |
| Approach: | They propose a Merge-then-Adapt framework for Personalized Large Language Models . they construct a shared Meta-LoRA bank and propose an Adaptive LoRA Fusion stage . |
| Outcome: | The proposed framework outperforms existing SOTA methods on the LaMP benchmark. |
The Elephant in the Room: Exploring the Role of Neutral Words in Language Model Group-Agnostic Debiasing (2025.findings-acl)
Copied to clipboard
Xinwei Guo, Jiashi Gao, Junlei Zhou, Jiaxin Zhang, Guanhua Chen, Xiangyu Zhao, Quanying Liu, Haiyan Wu, Xin Yao, Xuetao Wei
| Challenge: | Large Language Models (LLMs) are increasingly integrated into our daily lives, raising ethical concerns, especially about perpetuating stereotypes. |
| Approach: | They propose a method that incorporates a neutral word semantics-based loss function to alleviate the deterioration of the LMS during debiasing. |
| Outcome: | The proposed method alleviates the deterioration of the Language Modeling Score (LMS) by incorporating a neutral word semantics-based loss function. |
LLMs Trust Humans More, That’s a Problem! Unveiling and Mitigating the Authority Bias in Retrieval-Augmented Generation (2025.acl-long)
Copied to clipboard
Yuxuan Li, Xinwei Guo, Jiashi Gao, Guanhua Chen, Xiangyu Zhao, Jiaxin Zhang, Quanying Liu, Haiyan Wu, Xin Yao, Xuetao Wei
| Challenge: | Large language models (LLMs) generate outputs that stray from user input or contravene established knowledge. |
| Approach: | They propose a new phenomenon, Authority Bias, where LLMs favor one knowledge source over the other . they propose atomic information that generates conflicts and a Conflict Detection Enhanced Query framework . |
| Outcome: | The proposed framework reduces Authority bias in large language models . it detects conflicts, performs credibility assessment on conflicting paragraphs, and detects perturbed text . |
ImPart: Importance-Aware Delta-Sparsification for Improved Model Compression and Merging in LLMs (2025.acl-long)
Copied to clipboard
| Challenge: | Recent approaches to reduce resource requirements for task-specific large language models have been developed. |
| Approach: | They propose a delta compression approach that optimizes for importance of a model . they use SVD to dynamically adjust the sparsity ratios of different vectors based on their importance . |
| Outcome: | The proposed approach achieves state-of-the-art in retaining task-specific knowledge even at high sparsity ratios. |
Can LLMs Hear the Dogwhistle? (2026.findings-acl)
Copied to clipboard
Yifan Liu, Yi Lin, Xinwei Guo, Ziwei Wang, Jiaxin Zhang, Guanhua Chen, Haiyan Wu, Xiangyu Zhao, Xin Yao, Xuetao Wei
| Challenge: | Existing safety benchmarks focus on explicitly harmful content, but ignore context-dependent expressions such as dogwhistles. |
| Approach: | They propose a benchmark for evaluating LLM safety under dogwhistle-driven prompts . their findings expose a blind spot in current safety evaluation practices . |
| Outcome: | The proposed benchmark compared safety performance with toxic terms using dogwhistle-driven prompts. |
SeqAR: Jailbreak LLMs with Sequential Auto-Generated Characters (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing studies have focused on the potential misuse of large language models (LLMs) however, the ability to align LLMs with human values is still vulnerable to malicious attacks. |
| Approach: | They propose a red-teaming strategy to enhance LLM safety by using a framework to design jailbreak prompts automatically. |
| Outcome: | The proposed framework achieves attack success rates of 88% and 60% in cold-start scenarios. |
Modeling LLM Unlearning as an Asymmetric Two-Task Learning Problem (2026.acl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) are inherently dual-use and can be leveraged for both beneficial and harmful purposes. |
| Approach: | They propose a retention-prioritized gradient synthesis framework that decouples task-specific gradient extraction from conflict-aware combination. |
| Outcome: | The proposed method achieves tighter alignment on WMDP Bio and RWKU benchmarks. |