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

arXiv: https://arxiv.org/abs/2609.11955 · HTML: https://mlsanity.com/paper/2609.11955/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 22 references that are in the map.
- First posted on arXiv 6 Aug 2026.

## Builds on (most cited first, 21 of 21)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [FEVER: a large-scale dataset for Fact Extraction and VERification](https://mlsanity.com/paper/1803.05355/) (2018)
- [Graph of Thoughts: Solving Elaborate Problems with Large Language Models](https://mlsanity.com/paper/2308.09687/) (2023)
- [SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models](https://mlsanity.com/paper/2303.08896/) (2023)
- [Calibration of Pre-trained Transformers](https://mlsanity.com/paper/2003.07892/) (2020)
- [RARR: Researching and Revising What Language Models Say, Using Language Models](https://mlsanity.com/paper/2210.08726/) (2022)
- [Measuring Attribution in Natural Language Generation Models](https://mlsanity.com/paper/2112.12870/) (2021)
- [Get Your Vitamin C! Robust Fact Verification with Contrastive Evidence](https://mlsanity.com/paper/2103.08541/) (2021)
- [FEVEROUS: Fact Extraction and VERification Over Unstructured and Structured information](https://mlsanity.com/paper/2106.05707/) (2021)
- [Ask Me Anything: A simple strategy for prompting language models](https://mlsanity.com/paper/2210.02441/) (2022)
- [WiCE: Real-World Entailment for Claims in Wikipedia](https://mlsanity.com/paper/2303.01432/) (2023)
- [Re2G: Retrieve, Rerank, Generate](https://mlsanity.com/paper/2207.06300/) (2022)
- [Search-in-the-Chain: Interactively Enhancing Large Language Models with Search for Knowledge-intensive Tasks](https://mlsanity.com/paper/2304.14732/) (2023)
- [FIRE: Fact-checking with Iterative Retrieval and Verification](https://mlsanity.com/paper/2411.00784/) (2024)
- [A Guide to Misinformation Detection Data and Evaluation](https://mlsanity.com/paper/2411.05060/) (2024)
- [Laboratory-Scale AI: Open-Weight Models are Competitive with ChatGPT Even in Low-Resource Settings](https://mlsanity.com/paper/2405.16820/) (2024)
- [Consistency Is the Key: Detecting Hallucinations in LLM Generated Text By Checking Inconsistencies About Key Facts](https://mlsanity.com/paper/2511.12236/) (2025)

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

- [PANINI-DR: Controlled Deep Research through Generative Semantic Workspaces](https://mlsanity.com/paper/2610.15208/) (2026)

## Abstract (arXiv)

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.