activity
20162026
most citedEvaluating the Robustness of Neural Networks: An Extreme Value Theory Approach

158 citations · 241 across the 25 of their papers we have counts for

collaborators
Showing cs.CLShow all

6 papers · 1 filter

cs.CL2026

From Detection to Refusal: Safer LLMs via Circuit-Guided Weight Scaling

Kuan-Lin Chu, Chung-En Sun, Tsui-Wei Weng

Despite extensive alignment efforts, Large Language Models (LLMs) remain vulnerable to generating unsafe content under adversarial prompting, yet the internal mechanisms by which s…

cs.CL2026

Steer2Edit: From Activation Steering to Component-Level Editing

Chung-En Sun, Ge Yan, Zimo Wang +1

Steering methods influence Large Language Model behavior by identifying semantic directions in hidden representations, but are typically realized through inference-time activation…

cs.CL2025

Effective Skill Unlearning through Intervention and Abstention

Yongce Li, Chung-En Sun, Tsui-Wei Weng

Large language Models (LLMs) have demonstrated remarkable skills across various domains. Understanding the mechanisms behind their abilities and implementing controls over them is…

cs.CL2025

ThinkEdit: Interpretable Weight Editing to Mitigate Overly Short Thinking in Reasoning Models

Chung-En Sun, Ge Yan, Tsui-Wei Weng

Recent studies have shown that Large Language Models (LLMs) augmented with chain-of-thought (CoT) reasoning demonstrate impressive problem-solving abilities. However, in this work,…

cs.CL2024

Concept Bottleneck Large Language Models

Chung-En Sun, Tuomas Oikarinen, Berk Ustun +1

We introduce Concept Bottleneck Large Language Models (CB-LLMs), a novel framework for building inherently interpretable Large Language Models (LLMs). In contrast to traditional bl…

cs.CL2024

Iterative Self-Tuning LLMs for Enhanced Jailbreaking Capabilities

Chung-En Sun, Xiaodong Liu, Weiwei Yang +5

Recent research has shown that Large Language Models (LLMs) are vulnerable to automated jailbreak attacks, where adversarial suffixes crafted by algorithms appended to harmful quer…