Zhuoyun Li
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
AI×1
Frequent co-authors
Research Timeline
2026
Dive into Ambiguity: A*-Inspired Multi-Agents Commonsense Obfuscation Attack on LLM Prompts
The paper introduces an A*-inspired framework to generate highly effective and efficient adversarial prompts that cause LLMs to hallucinate commonsense errors while maintaining the original prompt's intent.
Highlighted terms show continued research focus across papers