Papers by Jiahe Liu
Beware of Your Po! Measuring and Mitigating AI Safety Risks in Role-Play Fine-Tuning of LLMs (2025.acl-long)
Copied to clipboard
Weixiang Zhao, Yulin Hu, Yang Deng, Jiahe Guo, Xingyu Sui, Xinyang Han, An Zhang, Yanyan Zhao, Bing Qin, Tat-Seng Chua, Ting Liu
| Challenge: | Existing role-play fine-tuning techniques improve role adaptability but may degrade safety performance, especially for villainous characters. |
| Approach: | They propose safety-aware Role-Play Fine-Tuning (SaRFT) to balance role-playing capabilities and safety. |
| Outcome: | The proposed method outperforms state-of-the-art baselines under both LoRA and full-parameter fine-tuning settings. |
MPO: Multilingual Safety Alignment via Reward Gap Optimization (2025.acl-long)
Copied to clipboard
Weixiang Zhao, Yulin Hu, Yang Deng, Tongtong Wu, Wenxuan Zhang, Jiahe Guo, An Zhang, Yanyan Zhao, Bing Qin, Tat-Seng Chua, Ting Liu
| Challenge: | Existing preference learning methods for safety alignment are monolingual and struggle with noisy multilingual data. |
| Approach: | They propose a multilingual reward gaP optimization approach that leverages the well-aligned safety capabilities of the dominant language to improve safety alignment across multiple languages. |
| Outcome: | Extensive experiments on three LLMs, LLaMA-3.1, Gemma-2 and Qwen2.5, validate MPO’s efficacy in multilingual safety alignment without degrading general multilingual utility. |
PsychEthicsBench: Evaluating Large Language Models Against Australian Mental Health Ethics (2026.findings-acl)
Copied to clipboard
Yaling Shen, Stephanie Fong, Yiwen Jiang, Zimu Wang, Feilong Tang, Qingyang Xu, Xiangyu Zhao, Zhongxing Xu, Jiahe Liu, Jinpeng Hu, Dominic Dwyer, Zongyuan Ge
| Challenge: | Mental disorders affect nearly one in seven people worldwide, yet the vast majority do not receive adequate care. |
| Approach: | They propose a framework to evaluate LLMs' ethical knowledge and behavioral responses through multiple-choice and open-ended tasks with fine-grained ethicality annotations. |
| Outcome: | Empirical results across 14 models reveal that refusal rates are poor indicators of ethical behavior, revealing a significant divergence between safety triggers and clinical appropriateness. |
Chain of Strategy Optimization Makes Large Language Models Better Emotional Supporter (2025.findings-emnlp)
Copied to clipboard
Weixiang Zhao, Xingyu Sui, Xinyang Han, Yang Deng, Yulin Hu, Jiahe Guo, Libo Qin, Qianyun Du, Shijin Wang, Yanyan Zhao, Bing Qin, Ting Liu
| Challenge: | Existing supervised fine-tuning (SFT) fails to address these issues, as it trains models on single gold-standard responses without modeling nuanced strategy trade-offs. |
| Approach: | They propose a two-stage framework that optimizes strategy selection preferences at each dialogue turn. |
| Outcome: | The proposed framework improves strategy selection preferences at each dialogue turn. |
AdaSteer: Your Aligned LLM is Inherently an Adaptive Jailbreak Defender (2025.emnlp-main)
Copied to clipboard
Weixiang Zhao, Jiahe Guo, Yulin Hu, Yang Deng, An Zhang, Xingyu Sui, Xinyang Han, Yanyan Zhao, Bing Qin, Tat-Seng Chua, Ting Liu
| Challenge: | Activation steering offers training-free defense but relies on fixed steering coefficients, resulting in suboptimal protection and increased false rejections of benign inputs. |
| Approach: | They propose an adaptive activation steering method that dynamically adjusts model behavior based on input characteristics. |
| Outcome: | The proposed method outperforms baseline methods across multiple jailbreak attacks with minimal impact on utility. |
Identifying Collective Intelligence Factor in LLM Agent Groups for Generalizable Multi-Agent System Design (2026.findings-acl)
Copied to clipboard
| Challenge: | Prior studies have focused on designing customized MAS for specific tasks . a critical research question remains: do LLM agent groups exhibit a form of "general intelligence" |
| Approach: | They find a Collective Intelligence factor in human groups that captures their general capability. |
| Outcome: | The proposed model predicts the ACI factor based on the features of LLM agent groups and can improve generalization abilities. |
CHiRPE: A Step Towards Real-World Clinical NLP with Clinician-Oriented Model Explanations (2026.eacl-short)
Copied to clipboard
Stephanie Fong, Zimu Wang, Guilherme C Oliveira, Xiangyu Zhao, Yiwen Jiang, Jiahe Liu, Beau-Luke Colton, Scott W. Woods, Martha Shenton, Barnaby Nelson, Zongyuan Ge, Dominic Dwyer
| Challenge: | Psychotic disorders are a major contributor to the global health burden due to their relatively high mortality risk. |
| Approach: | They propose an NLP pipeline that takes semi-structured clinical interviews to predict psychosis risk and generate novel SHAP explanation formats. |
| Outcome: | The proposed pipeline outperforms baseline models and achieves 90% accuracy across three BERT variants. |