3 papers
cs.CL2026
ACR: Adaptive Context Refactoring via Context Refactoring Operators for Multi-Turn Dialogue
Jiawei Shen, Jia Zhu, Hanghui Guo +9
Large Language Models (LLMs) have shown remarkable performance in multi-turn dialogue. However, in multi-turn dialogue, models still struggle to stay aligned with what has been est…
cs.CR2025
ForgeDAN: An Evolutionary Framework for Jailbreaking Aligned Large Language Models
Siyang Cheng, Gaotian Liu, Rui Mei +7
The rapid adoption of large language models (LLMs) has brought both transformative applications and new security risks, including jailbreak attacks that bypass alignment safeguards…
cs.CL2024
Improving Autoregressive Training with Dynamic Oracles
Jianing Yang, Harshine Visvanathan, Yilin Wang +2
Many tasks within NLP can be framed as sequential decision problems, ranging from sequence tagging to text generation. However, for many tasks, the standard training methods, inclu…