Papers by Xiaohui Kuang
Refusal-Aware Red Teaming: Exposing Inconsistency in Safety Evaluations (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) require rigorous safety evaluations to be effective. |
| Approach: | They propose a red teaming framework that detects internal model refusals and contrasts them with judgments from an external safety evaluator to generate test cases that expose such discrepancies. |
| Outcome: | The proposed framework outperforms existing reinforcement learning-based approaches in generating diverse test cases and achieves a substantially higher discovery rate of refusal gaps. |
Better Red Teaming via Searching with Large Language Model (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for evaluating large language models face challenges in managing semantic intricacies and optimizing the efficiency of the search process. |
| Approach: | They propose a framework that reconceptualizes test case generation as a strategic planning problem, leveraging Monte Carlo Tree Search. |
| Outcome: | Experiments on a range of LLM architectures show that the proposed framework achieves state-of-the-art attack success rates without sacrificing computational efficiency. |
Code Vulnerability Detection via Nearest Neighbor Mechanism (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods to learn code semantics from source code are difficult to identify. |
| Approach: | They propose a method which retrieves multiple neighbor samples and utilizes label information to provide help for model predictions. |
| Outcome: | Extensive experiments show that the proposed method can achieve obvious performance improvements compared to baseline models. |
Joint Geometrical and Statistical Domain Adaptation for Cross-domain Code Vulnerability Detection (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to detect code vulnerability are limited by labeled training data on target domains. |
| Approach: | They propose a cross-domain code vulnerability detection framework called MNCRI . they propose mutual nearest neighbor contrastive learning to align the source and target domains . |
| Outcome: | The proposed framework outperforms state-of-the-art methods in cross-domain code vulnerability detection tasks. |