Debating the Unspoken: Role-Anchored Multi-Agent Reasoning for Half-Truth Detection
cs.CL
Submitted: 2026-04-21
Updated: 2026-09-07
Comments: Accepted by EMNLP 2026
Code: https://github.com/tangyixuan/RADAR
License: http://creativecommons.org/licenses/by-nc-nd/4.0/
The gist: Half-truths, claims that are factually correct yet misleading due to omitted context, remain a blind spot for fact verification systems focused on explicit falsehoods.
Terminology
Abstract
Half-truths, claims that are factually correct yet misleading due to omitted context, remain a blind spot for fact verification systems focused on explicit falsehoods. Addressing such omission-based manipulation requires reasoning not only about what is said, but also about what is left unsaid. We propose RADAR, a role-anchored multi-agent debate framework for omission-aware fact verification under realistic, noisy retrieval. RADAR assigns complementary roles to a Politician and a Scientist, who reason adversarially over shared retrieved evidence, moderated by a neutral Judge. A dual-threshold early termination controller adaptively decides when sufficient reasoning has been reached to issue a verdict. Experiments show that RADAR consistently outperforms strong single- and multi-agent baselines across datasets and backbones, improving omission detection accuracy while reducing reasoning cost. These results demonstrate that role-anchored, retrieval-grounded debate with adaptive control is an effective and scalable framework for uncovering missing context in fact verification. The code is available at https://github.com/tangyixuan/RADAR.
Sources
- GPT-4 Technical Report
- Automated Fact-Checking of Climate Change Claims with Large Language Models
- "Beware of deception": Detecting Half-Truth and Debunking it through Controlled Claim Editing
- Contrastive Learning to Improve Retrieval for Real-world Fact Checking
- Literature Review Of Multi-Agent Debate For Problem-Solving
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering