Papers by Xiaofei Wen

4 papers
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

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.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations