collaborators

6 papers

cs.CL2026

Write, Execute, Refine: From Skill Followers to Skill Optimizers via Reinforcement Learning from Execution Feedback

Kang Peng, Zhiwei Zhang, Yichen Zhang +7

Expert-written natural language skills can improve tool-using agents, yet agent-authored skills perform 8-11 points worse than using no skill. This gap suggests that following proc…

eess.AS2026

UAT: Unified Audio-Text Diffusion for Audio Generation, Editing, and Captioning

Hui Wang, Yifan Yang, Zeyue Tian +8

Audio generation and audio-to-text understanding remain largely separate, with diffusion models dominating high-fidelity synthesis and autoregressive (AR) language models driving c…

cs.CR2026

BAIT: Boundary-Guided Disclosure Escalation via Self-Conditioned Reasoning

Xuan Luo, Yue Wang, Geng Tu +2

In this work, we propose BAIT (Boundary-Aware Iterative Trap), a three-step jailbreak framework that approaches malicious goals through internal disclosure. BAIT first asks the mod…

cs.CL2026

Evaluating Proactive Risk Awareness of Large Language Models

Xuan Luo, Yubin Chen, Zhiyu Hou +4

As large language models (LLMs) are increasingly embedded in everyday decision-making, their safety responsibilities extend beyond reacting to explicit harmful intent toward antici…

cs.CR2026

A Simple and Efficient Jailbreak Method Exploiting LLMs' Helpfulness

Xuan Luo, Yue Wang, Zefeng He +3

This study reveals a critical safety blind spot in modern LLMs: learning-style queries, which closely resemble ordinary educational questions, can reliably elicit harmful responses…

cs.CL2025

CoreEval: Automatically Building Contamination-Resilient Datasets with Real-World Knowledge toward Reliable LLM Evaluation

Jingqian Zhao, Bingbing Wang, Geng Tu +5

Data contamination poses a significant challenge to the fairness of LLM evaluations in natural language processing tasks by inadvertently exposing models to test data during traini…