# Debating the Unspoken: Role-Anchored Multi-Agent Reasoning for Half-Truth Detection

arXiv: https://arxiv.org/abs/2604.19005 · HTML: https://mlsanity.com/paper/2604.19005/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 33 references that are in the map.
- First posted on arXiv 21 Apr 2026.

## Builds on (most cited first, 20 of 20)

- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [FEVER: a large-scale dataset for Fact Extraction and VERification](https://mlsanity.com/paper/1803.05355/) (2018)
- [Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate](https://mlsanity.com/paper/2305.19118/) (2023)
- [AVeriTeC: A Dataset for Real-world Claim Verification with Evidence from the Web](https://mlsanity.com/paper/2305.13117/) (2023)
- [Fine-Grained Analysis of Propaganda in News Articles](https://mlsanity.com/paper/1910.02517/) (2019)
- [Towards LLM-based Fact Verification on News Claims with a Hierarchical Step-by-Step Prompting Method](https://mlsanity.com/paper/2310.00305/) (2023)
- [Fighting the COVID-19 Infodemic: Modeling the Perspective of Journalists, Fact-Checkers, Social Media Platforms, Policy Makers, and the Society](https://mlsanity.com/paper/2005.00033/) (2020)
- [FIRE: Fact-checking with Iterative Retrieval and Verification](https://mlsanity.com/paper/2411.00784/) (2024)
- [GERE: Generative Evidence Retrieval for Fact Verification](https://mlsanity.com/paper/2204.05511/) (2022)
- [Do Multi-Hop Question Answering Systems Know How to Answer the Single-Hop Sub-Questions?](https://mlsanity.com/paper/2002.09919/) (2020)
- [The Truth Becomes Clearer Through Debate! Multi-Agent Systems with Large Language Models Unmask Fake News](https://mlsanity.com/paper/2505.08532/) (2025)
- [Retrieval Augmented Fact Verification by Synthesizing Contrastive Arguments](https://mlsanity.com/paper/2406.09815/) (2024)
- [Literature Review Of Multi-Agent Debate For Problem-Solving](https://mlsanity.com/paper/2506.00066/) (2025)
- [Debate-to-Detect: Reformulating Misinformation Detection as a Real-World Debate with Large Language Models](https://mlsanity.com/paper/2505.18596/) (2025)
- [The Missing Parts: Augmenting Fact Verification with Half-Truth Detection](https://mlsanity.com/paper/2508.00489/) (2025)
- [Deception through Half-Truths](https://mlsanity.com/paper/1911.05885/) (2019)
- [To Tell The Truth: Language of Deception and Language Models](https://mlsanity.com/paper/2311.07092/) (2023)
- [Contrastive Learning to Improve Retrieval for Real-world Fact Checking](https://mlsanity.com/paper/2410.04657/) (2024)
- [False Information, Bots and Malicious Campaigns: Demystifying Elements of Social Media Manipulations](https://mlsanity.com/paper/2308.12497/) (2023)
- [What's in the News? Towards Identification of Bias by Commission, Omission, and Source Selection (COSS)](https://mlsanity.com/paper/2508.02540/) (2025)

## Built on by (most cited first, 1 of 1)

- [Locating Answer-Correctness Signals in Frozen Large Language Models](https://mlsanity.com/paper/2609.37700/) (2026)

## Abstract (arXiv)

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.