{"slug": "r2vc-modular-fact-checking-with-retrieval-verification-and-confidence", "title": "R2VC: Modular Fact-Checking with Retrieval, Verification, and Confidence Calibration", "summary": "Researchers introduced R2VC, a modular retrieve, reason, verify, and calibrate architecture for evidence-grounded fact checking, reporting that an 8B backbone with R2VC achieves 13.74% higher accuracy on FEVER than baseline. Ablation studies found that removing verifier-based candidate selection drops FEVER accuracy to 76.24%, while removing confidence calibration nearly doubles the Brier score to 0.161. A manual analysis of 250 errors showed retrieval failures, especially wrong-entity evidence, remain the dominant bottleneck.", "body_md": "arXiv:2609.11955v1 Announce Type: new \nAbstract: Large language models are increasingly used for automated fact checking, but end-to-end prompting often entangles evidence retrieval, reasoning, and uncertainty estimation, making failures difficult to diagnose and confidence difficult to trust. We present R2VC, a modular retrieve, reason, verify, calibrate architecture for evidence-grounded fact checking with citations and abstention. R2VC combines hybrid sparse+dense retrieval over Wikipedia, a supervised fine-tuned and DPO-aligned generator that produces diverse structured verdict candidates, an external NLI cross-encoder for evidence-based candidate selection, and a lightweight sequence-level calibrator for confidence estimation and selective abstention. On FEVER, an 8B backbone with R2VC achieves 13.74% higher accuracy than baseline. Ablation studies show that verifier-based candidate selection and confidence calibration are the largest contributors to performance. Removing candidate selection drops FEVER accuracy to 76.24%, while removing calibration nearly doubles the Brier score to 0.161. A manual analysis of 250 errors further shows that retrieval failures, especially wrong-entity evidence, remain the dominant bottleneck. Together, these results show that modular fact-checking pipelines can substantially improve both predictive accuracy and confidence reliability in open-domain verification.", "url": "https://wpnews.pro/news/r2vc-modular-fact-checking-with-retrieval-verification-and-confidence", "canonical_source": "https://arxiv.org/abs/2609.11955", "published_at": "2026-09-14 04:00:00+00:00", "updated_at": "2026-09-14 04:27:37.085477+00:00", "lang": "en", "topics": ["artificial-intelligence", "natural-language-processing", "ai-research", "large-language-models", "ai-safety"], "entities": ["R2VC", "FEVER", "Wikipedia", "DPO", "NLI"], "alternates": {"html": "https://wpnews.pro/news/r2vc-modular-fact-checking-with-retrieval-verification-and-confidence", "markdown": "https://wpnews.pro/news/r2vc-modular-fact-checking-with-retrieval-verification-and-confidence.md", "text": "https://wpnews.pro/news/r2vc-modular-fact-checking-with-retrieval-verification-and-confidence.txt", "jsonld": "https://wpnews.pro/news/r2vc-modular-fact-checking-with-retrieval-verification-and-confidence.jsonld"}}