# SUCEA: Reasoning-Intensive Retrieval for Adversarial Fact-checking through Claim Decomposition and Editing

arXiv: https://arxiv.org/abs/2506.04583 · HTML: https://mlsanity.com/paper/2506.04583/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 21 of its 43 references that are in the map.
- First posted on arXiv 5 Jun 2025.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

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

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://mlsanity.com/paper/2305.14251/) (2023)
- [Unsupervised Dense Information Retrieval with Contrastive Learning](https://mlsanity.com/paper/2112.09118/) (2021)
- [Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agents](https://mlsanity.com/paper/2304.09542/) (2023)
- [BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval](https://mlsanity.com/paper/2407.12883/) (2024)
- [Fact-Checking Complex Claims with Program-Guided Reasoning](https://mlsanity.com/paper/2305.12744/) (2023)
- [WiCE: Real-World Entailment for Claims in Wikipedia](https://mlsanity.com/paper/2303.01432/) (2023)
- [Making Text Embedders Few-Shot Learners](https://mlsanity.com/paper/2409.15700/) (2024)
- [Reliable, Adaptable, and Attributable Language Models with Retrieval](https://mlsanity.com/paper/2403.03187/) (2024)
- [Generating Literal and Implied Subquestions to Fact-check Complex Claims](https://mlsanity.com/paper/2205.06938/) (2022)
- [Generating Fact Checking Briefs](https://mlsanity.com/paper/2011.05448/) (2020)
- [Fool Me Twice: Entailment from Wikipedia Gamification](https://mlsanity.com/paper/2104.04725/) (2021)
- [DocMath-Eval: Evaluating Math Reasoning Capabilities of LLMs in Understanding Long and Specialized Documents](https://mlsanity.com/paper/2311.09805/) (2023)
- [Molecular Facts: Desiderata for Decontextualization in LLM Fact Verification](https://mlsanity.com/paper/2406.20079/) (2024)
- [FinanceMath: Knowledge-Intensive Math Reasoning in Finance Domains](https://mlsanity.com/paper/2311.09797/) (2023)
- [FinDVer: Explainable Claim Verification over Long and Hybrid-Content Financial Documents](https://mlsanity.com/paper/2411.05764/) (2024)
- [FACTOID: FACtual enTailment fOr hallucInation Detection](https://mlsanity.com/paper/2403.19113/) (2024)
- [Trick Me If You Can: Human-in-the-loop Generation of Adversarial Examples for Question Answering](https://mlsanity.com/paper/1809.02701/) (2018)

## Built on by (most cited first, 2 of 2)

- [Harnessing LLM Agents with Skill Programs](https://mlsanity.com/paper/2605.17734/) (2026)
- [Memory Is a Derivation: The Distributed-Evidence Paradox in Long-Term Agents](https://mlsanity.com/paper/2609.36130/) (2026)

## Abstract (arXiv)

Automatic fact-checking has recently received more attention as a means of combating misinformation. Despite significant advancements, fact-checking systems based on retrieval-augmented language models still struggle to tackle adversarial claims, which are intentionally designed by humans to challenge fact-checking systems. To address these challenges, we propose a training-free method designed to rephrase the original claim, making it easier to locate supporting evidence. Our modular framework, SUCEA, decomposes the task into three steps: 1) Claim Segmentation and Decontextualization that segments adversarial claims into independent sub-claims; 2) Iterative Evidence Retrieval and Claim Editing that iteratively retrieves evidence and edits the subclaim based on the retrieved evidence; 3) Evidence Aggregation and Label Prediction that aggregates all retrieved evidence and predicts the entailment label. Experiments on two challenging fact-checking datasets demonstrate that our framework significantly improves on both retrieval and entailment label accuracy, outperforming four strong claim-decomposition-based baselines.