Showing cs.CLShow all
3 papers · 1 filter
cs.CL2026
ICO: Enhancing Semantic-Shift Jailbreaks via Iterative Context Optimization
Hujian Zhu, Yihao Huang, Felix Juefei-Xu +5
Foundation models have achieved remarkable success across diverse tasks, but they remain vulnerable. To investigate such vulnerabilities, semantic-shift jailbreaks have recently em…
cs.CL2026
Understanding, Detecting, and Repairing Real-World In-Context-Learning-Based Text-to-SQL Errors
Jiawei Shen, Chengcheng Wan, Ruoyi Qiao +6
Large language models (LLMs) have been adopted for text-to-SQL tasks, utilizing their in-context learning (ICL) capability to translate natural language questions into SQL queries.…
cs.CL2025
Efficient Universal Goal Hijacking with Semantics-guided Prompt Organization
Yihao Huang, Chong Wang, Xiaojun Jia +5
Universal goal hijacking is a kind of prompt injection attack that forces LLMs to return a target malicious response for arbitrary normal user prompts. The previous methods achieve…