Multi-Agent Systems2 min read
Debate to Deceive: Poisoning LLM's Fact-Checking via Game-Theoretic Multi-Agent Debate
Knowledge attacks on Large Language Models, such as manipulating fact-checking judgments, pose significant risks to AI reliability. Existing approaches -- adversarial suffix/template injection and single-agent self-reflection -- lack robustness across diverse defenses and are prone to confirmation…
By Liting Huang, Huizhi Liang, Yi Lei, Xingjun Ma, Varun OjhaarXiv - cs.AI
Read the full story
Originally published by arXiv - cs.AI on Nov 9, 2026.
Comments
Sign in to join the discussion.