Debating the Unspoken: Role-Anchored Multi-Agent Reasoning for Half-Truth Detection¶
Conference: ACL 2026 arXiv: 2604.19005 Code: https://github.com/tangyixuan/RADAR Area: Fact Verification / Misinformation Detection Keywords: Half-Truth Detection, Multi-Agent Debate, Omission Reasoning, Role Anchoring, Adaptive Termination
TL;DR¶
RADAR uses role-anchored (politician vs scientist) multi-agent debate to detect half-truths — statements that are factually correct but misleading due to omitted context — with dual-threshold adaptive early stopping, consistently outperforming single-agent and traditional multi-agent baselines under noisy retrieval conditions.
Method¶
Key Designs¶
-
Role-Anchored Debate Protocol: Politician agent constructs the most persuasive supporting narrative (confirmatory reasoning); scientist agent probes for missing, weak, or selectively presented information (analytical reasoning). The contrast naturally models half-truth creation and detection mechanisms.
-
Dual-Threshold Adaptive Early Stopping: Terminates only when stop margin \(s \geq \tau_s\) AND maximum label confidence \(c \geq \tau_v\) are both met, preventing premature stopping on uncertain cases.
-
Retrieval-Anchored Evidence Sharing: All agents share the same evidence pool, grounding arguments in retrieved evidence rather than parametric knowledge.
Key Experimental Results¶
| Method | Accuracy | F1_macro | F1_HalfTrue |
|---|---|---|---|
| D2D (MAD) | 63.0 | 50.9 | 39.7 |
| RADAR_multi | 77.7 | 63.3 | 56.5 |
Highlights & Insights¶
- The "politician-scientist" role metaphor is ingenious — half-truths are common in political discourse, and using agents that model this discourse strategy to detect them creates a "fighting fire with fire" design philosophy
- Paradigm shift from "finding contradictions" to "discovering omissions" opens new directions for fact verification
Rating¶
- Novelty: ⭐⭐⭐⭐⭐
- Experimental Thoroughness: ⭐⭐⭐⭐
- Writing Quality: ⭐⭐⭐⭐⭐
- Value: ⭐⭐⭐⭐⭐