Papers by Chung-En Sun
ThinkEdit: Interpretable Weight Editing to Mitigate Overly Short Thinking in Reasoning Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies have shown that Large Language Models (LLMs) augmented with chain-of-thought (CoT) reasoning demonstrate impressive problem-solving abilities. |
| Approach: | They propose a weight-editing approach to reduce overly short reasoning by steering the model along a linear direction in the representation space. |
| Outcome: | The proposed model reduces overly short reasoning and yields significant accuracy gains on multiple math benchmarks. |
Iterative Self-Tuning LLMs for Enhanced Jailbreaking Capabilities (2025.naacl-long)
Copied to clipboard
Chung-En Sun, Xiaodong Liu, Weiwei Yang, Tsui-Wei Weng, Hao Cheng, Aidan San, Michel Galley, Jianfeng Gao
| Challenge: | Recent research shows that Large Language Models (LLMs) are vulnerable to automated jailbreak attacks. |
| Approach: | They propose a framework that crafts adversarial LLMs with enhanced jailbreak ability. |
| Outcome: | ADV-LLM significantly reduces the computational cost of generating adversarial suffixes while achieving nearly 100% ASR on various open-source LLMs. |
Effective Skill Unlearning through Intervention and Abstention (2025.naacl-long)
Copied to clipboard
| Challenge: | Large language models exhibit remarkable skills across various domains without training on task-specific datasets. |
| Approach: | They propose two lightweight, training-free machine skill unlearning techniques for LLMs . they propose to unlearning a particular skill while retaining overall capabilities . |
| Outcome: | The proposed methods demonstrate strong unlearning capabilities for the designated skills across seven different languages. |