# Retrieve-Refine-Calibrate: A Framework for Complex Claim Fact-Checking

arXiv: https://arxiv.org/abs/2601.16555 · HTML: https://mlsanity.com/paper/2601.16555/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 29 references that are in the map.
- First posted on arXiv 23 Jan 2026.

## Builds on (most cited first, 23 of 23)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing](https://mlsanity.com/paper/2111.09543/) (2021)
- [DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence](https://mlsanity.com/paper/2401.14196/) (2024)
- [SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models](https://mlsanity.com/paper/2303.08896/) (2023)
- [Adversarial NLI: A New Benchmark for Natural Language Understanding](https://mlsanity.com/paper/1910.14599/) (2019)
- [A Survey on Automated Fact-Checking](https://mlsanity.com/paper/2108.11896/) (2021)
- [LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention](https://mlsanity.com/paper/2010.01057/) (2020)
- [A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs by Validating Low-Confidence Generation](https://mlsanity.com/paper/2307.03987/) (2023)
- [HoVer: A Dataset for Many-Hop Fact Extraction And Claim Verification](https://mlsanity.com/paper/2011.03088/) (2020)
- [Fact-Checking Complex Claims with Program-Guided Reasoning](https://mlsanity.com/paper/2305.12744/) (2023)
- [Automated Fact Checking: Task formulations, methods and future directions](https://mlsanity.com/paper/1806.07687/) (2018)
- [BERT for Evidence Retrieval and Claim Verification](https://mlsanity.com/paper/1910.02655/) (2019)
- [Learning to Explain: Datasets and Models for Identifying Valid Reasoning Chains in Multihop Question-Answering](https://mlsanity.com/paper/2010.03274/) (2020)
- [Explainable Claim Verification via Knowledge-Grounded Reasoning with Large Language Models](https://mlsanity.com/paper/2310.05253/) (2023)
- [Decomposition Dilemmas: Does Claim Decomposition Boost or Burden Fact-Checking Performance?](https://mlsanity.com/paper/2411.02400/) (2024)
- [Explainable Fact-checking through Question Answering](https://mlsanity.com/paper/2110.05369/) (2021)
- [BiDeV: Bilateral Defusing Verification for Complex Claim Fact-Checking](https://mlsanity.com/paper/2502.16181/) (2025)
- [Detecting Check-Worthy Claims in Political Debates, Speeches, and Interviews Using Audio Data](https://mlsanity.com/paper/2306.05535/) (2023)
- [DSLR: Document Refinement with Sentence-Level Re-ranking and Reconstruction to Enhance Retrieval-Augmented Generation](https://mlsanity.com/paper/2407.03627/) (2024)
- [Entity-aware Cross-lingual Claim Detection for Automated Fact-checking](https://mlsanity.com/paper/2503.15220/) (2025)

## Abstract (arXiv)

Fact-checking aims to verify the truthfulness of a claim based on the retrieved evidence. Existing methods typically follow a decomposition paradigm, in which a claim is broken down into sub-claims that are individually verified. However, the decomposition paradigm may introduce noise to the verification process due to irrelevant entities or evidence, ultimately degrading verification accuracy. To address this problem, we propose a Retrieve-Refine-Calibrate (RRC) framework based on large language models (LLMs). Specifically, the framework first identifies the entities mentioned in the claim and retrieves evidence relevant to them. Then, it refines the retrieved evidence based on the claim to reduce irrelevant information. Finally, it calibrates the verification process by re-evaluating low-confidence predictions. Experiments on two popular fact-checking datasets (HOVER and FEVEROUS-S) demonstrate that our framework achieves superior performance compared with competitive baselines.