Debate to Deceive: Poisoning LLM's Fact-Checking via Game-Theoretic Multi-Agent Debate
cs.AI
Submitted: 2026-11-05
Updated: 2026-11-05
Terminology
Sources
- Detecting Language Model Attacks with Perplexity
- CLIMATE-FEVER: A Dataset for Verification of Real-World Climate Claims
- Game-theoretic LLM: Agent Workflow for Negotiation Games
- Baseline Defenses for Adversarial Attacks Against Aligned Language Models
- Game Theory Meets Large Language Models: A Systematic Survey with Taxonomy and New Frontiers
- A Generalised Method for Empirical Game Theoretic Analysis
- ADMIT: Few-shot Knowledge Poisoning Attacks on RAG-based Fact Checking
- Practical Poisoning Attacks against Retrieval-Augmented Generation
- Universal and Transferable Adversarial Attacks on Aligned Language Models
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents