Co-FactChecker improves human-AI claim verification by translating expert feedback into direct edits on the model's reasoning trace, outperforming dialogue-based and autonomous baselines in both automatic and human evaluations.
Together, when we win in November, we are finally going to pass universal background checks, red flag laws, and an assault weapons ban
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Co-FactChecker: A Framework for Human-AI Collaborative Claim Verification Using Large Reasoning Models
Co-FactChecker improves human-AI claim verification by translating expert feedback into direct edits on the model's reasoning trace, outperforming dialogue-based and autonomous baselines in both automatic and human evaluations.