Looking Into The Past: The Impact of Context on Detecting Deceptive Statements

arXiv:2610.27407v1 Announce Type: new Abstract: Deception detection typically considers messages in isolation. Previous works in claim verification and role detection have displayed that additional information such as gameplay history is crucial to successful predictions. In this work, we demonstrate the value of preceding gameplay dialogue when applied to deceptive message detection within the hidden role game of Avalon. The findings show that LLMs can see improvement across a number of metrics, including accuracy by up to 31% with the addition of gameplay context for the target message.

Related

• ContextClaim: A Context-Driven Paradigm for Verifiable Claim Detection
• Effective Dense Retrieval using Only In-Context Examples
• How Robust Is Multimodal Claim Verification to LLM Rewriting?
• Why Static Probes Fail: Context Determines Deception Feature Composition

Source: arXiv cs.CL | 2026-10-21