Papers by Xiaofei Wen
Red Teaming Language Models for Processing Contradictory Dialogues (2024.emnlp-main)
Copied to clipboard
| Challenge: | a recent study shows that language models are prone to self-contradiction during dialogues. |
| Approach: | They propose a red teaming framework that detects and attempts to explain dialogues, then modifies existing contradictory content using the explanation. |
| Outcome: | The proposed task improves the ability to detect contradictory dialogues and provides valid explanations. |
RedCoder: Automated Multi-Turn Red Teaming for Code LLMs (2026.acl-long)
Copied to clipboard
Wenjie Jacky Mo, Qin Liu, Xiaofei Wen, Dongwon Jung, Hadi Askari, Wenxuan Zhou, Zhe Zhao, Muhao Chen
| Challenge: | Existing red-teaming approaches for code generation rely on extensive human effort and are prone to generating malicious code under adversarial environments. |
| Approach: | They propose a red-teaming agent that engages victim models in multi-turn conversations to elicit vulnerable code. |
| Outcome: | Experiments show that RedCoder outperforms red-teaming methods in inducing vulnerabilities in code generation. |
ThinkGuard: Deliberative Slow Thinking Leads to Cautious Guardrails (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing guardrails rely on rule-based filtering or single-pass classification, limiting their ability to handle nuanced safety violations. |
| Approach: | They propose a critique-augmented guardrail model that distills knowledge from high-capacity LLMs by generating structured critiques alongside safety labels. |
| Outcome: | The proposed model outperforms existing guardrail models on multiple safety benchmarks and achieves the highest average F1 and AUPRC. |
Personalized Topic Selection Model for Topic-Grounded Dialogue (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing topic-grounded dialogue systems tend to predict user-uninteresting and contextually irrelevant topics due to noise within side information sources. |
| Approach: | They propose a personalized topic selection model for topic-grounded dialogue that selectively aggregates side information to generate engaging responses. |
| Outcome: | The proposed model outperforms state-of-the-art models on multiple evaluation metrics. |