mlsanityData to 7 Oct 2026

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

arXiv 2506.04583 ↗First posted 5 Jun 2025cs.CL cs.AIcited by 2

On the map: LLM reasoning → Reasoning benchmarks and evaluation

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.

Key facts. Cited by 2 papers in the map (data through 7 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.

Builds on

21 of 43 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023Fact-Checking Complex Claims with Program-Guided Reasoning22 May

Other references · 20

  1. 2024The Llama 3 Herd of Modelscited by 14,192
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  3. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  4. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,185
  5. 2023FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generationcited by 1,259
  6. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,203
  7. 2023Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agentscited by 356
  8. 2024BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrievalcited by 153
  9. 2023WiCE: Real-World Entailment for Claims in Wikipediacited by 118
  10. 2024Making Text Embedders Few-Shot Learnerscited by 78
  11. 2024Reliable, Adaptable, and Attributable Language Models with Retrievalcited by 73
  12. 2022Generating Literal and Implied Subquestions to Fact-check Complex Claimscited by 66
8 more
  1. 2020Generating Fact Checking Briefscited by 50
  2. 2021Fool Me Twice: Entailment from Wikipedia Gamificationcited by 50
  3. 2023DocMath-Eval: Evaluating Math Reasoning Capabilities of LLMs in Understanding Long and Specialized Documentscited by 45
  4. 2024Molecular Facts: Desiderata for Decontextualization in LLM Fact Verificationcited by 42
  5. 2023FinanceMath: Knowledge-Intensive Math Reasoning in Finance Domainscited by 39
  6. 2024FinDVer: Explainable Claim Verification over Long and Hybrid-Content Financial Documentscited by 19
  7. 2024FACTOID: FACtual enTailment fOr hallucInation Detectioncited by 10
  8. 2018Trick Me If You Can: Human-in-the-loop Generation of Adversarial Examples for Question Answeringcited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Harnessing LLM Agents with Skill Programscited by 7
  2. 2026Memory Is a Derivation: The Distributed-Evidence Paradox in Long-Term Agentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026DECEIVE-AFC: Adversarial Claim Attacks against Search-Enabled LLM-based Fact-Checking Systems
  2. 2025Althea: The Fact-Checking--Metalearning Tradeoff in AI-Assisted Verification
  3. 2025ADMIT: Few-shot Knowledge Poisoning Attacks on RAG-based Fact Checking
  4. 2026Mask-to-Correct^+: Leveraging Retriever Diversity for Masking-guided Faithful Fact Correction
  5. 2024Retrieval Augmented Fact Verification by Synthesizing Contrastive Arguments
  6. 2026ToE: A Hierarchical and Explainable Claim Verification Framework with Dynamic Multi-source Evidence Retrieval and Aggregation
  7. 2025Beyond Retrieval: Improving Evidence Quality for LLM-based Multimodal Fact-Checking
  8. 2025Debate-to-Detect: Reformulating Misinformation Detection as a Real-World Debate with Large Language Models