cd /news/artificial-intelligence/r2vc-modular-fact-checking-with-retr… · home topics artificial-intelligence article
[ARTICLE · art-128721] src=arxiv.org ↗ pub= topic=artificial-intelligence verified=true sentiment=↑ positive

R2VC: Modular Fact-Checking with Retrieval, Verification, and Confidence Calibration

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.

by read1 min views1 publishedSep 14, 2026

arXiv:2609.11955v1 Announce Type: new Abstract: 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.

── more in #artificial-intelligence 4 stories · sorted by recency
── more on @r2vc 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/r2vc-modular-fact-ch…] indexed:0 read:1min 2026-09-14 ·