mlsanityData to 14 Oct 2026

Enhancing Factual Accuracy and Citation Generation in LLMs via Multi-Stage Self-Verification

arXiv 2509.05741 ↗First posted 6 Sep 2025cs.CLcited by 0

On the map: LLM reasoning → Hallucination detection and mitigation

Abstract (arXiv)

This research introduces VeriFact-CoT (Verified Factual Chain-of-Thought), a novel method designed to address the pervasive issues of hallucination and the absence of credible citation sources in Large Language Models (LLMs) when generating complex, fact-sensitive content. By incorporating a multi-stage mechanism of 'fact verification-reflection-citation integration,' VeriFact-CoT empowers LLMs to critically self-examine and revise their intermediate reasoning steps and final answers. This process significantly enhances the objective accuracy, trustworthiness, and traceability of the generated outputs, making LLMs more reliable for applications demanding high fidelity such as scientific research, news reporting, and legal consultation.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Hallucination detection and mitigation, one of 17 directions in LLM reasoning. Builds on 22 of its 27 references that are in the map. First posted on arXiv 6 Sep 2025.

Builds on

22 of 27 references.

References · 22

  1. 2020Answering Complex Open-Domain Questions with Multi-Hop Dense Retrievalcited by 162
  2. 2023Structured Chain-of-Thought Prompting for Code Generationcited by 138
  3. 2024Visual In-Context Learning for Large Vision-Language Modelscited by 128
  4. 2023Automatic Prompt Augmentation and Selection with Chain-of-Thought from Labeled Datacited by 119
  5. 2022Evaluating the Factual Consistency of Large Language Models Through News Summarizationcited by 92
  6. 2024The Dawn After the Dark: An Empirical Study on Factuality Hallucination in Large Language Modelscited by 88
  7. 2024Enhancing Code LLMs with Reinforcement Learning in Code Generation: A Surveycited by 83
  8. 2023Mitigating Large Language Model Hallucinations via Autonomous Knowledge Graph-based Retrofittingcited by 70
  9. 2024Large Language Models have Intrinsic Self-Correction Abilitycited by 46
  10. 2025Improving Medical Large Vision-Language Models with Abnormal-Aware Feedbackcited by 42
  11. 2025SCORE: Story Coherence and Retrieval Enhancement for AI Narrativescited by 42
  12. 2025Hyper-RAG: Combating LLM Hallucinations using Hypergraph-Driven Retrieval-Augmented Generationcited by 23
10 more
  1. 2022Cedille: A large autoregressive French language modelcited by 20
  2. 2024Do Advanced Language Models Eliminate the Need for Prompt Engineering in Software Engineering?cited by 19
  3. 2025System Prompt Optimization with Meta-Learningcited by 18
  4. 2024Large Language Models as Software Components: A Taxonomy for LLM-Integrated Applicationscited by 17
  5. 2025Uncertainty-Aware Fusion: An Ensemble Framework for Mitigating Hallucinations in Large Language Modelscited by 12
  6. 2024Enhanced Visual SLAM for Collision-free Driving with Lightweight Autonomous Carscited by 6
  7. 2025Zero-knowledge LLM hallucination detection and mitigation through fine-grained cross-model consistencycited by 6
  8. 2024Prompt Bakingcited by 5
  9. 2025MultiHal: Multilingual Dataset for Knowledge-Graph Grounded Evaluation of LLM Hallucinationscited by 2
  10. 2025ResNetVLLM-2: Addressing ResNetVLLM's Multi-Modal Hallucinationscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Hallucination to Truth: A Review of Fact-Checking and Factuality Evaluation in Large Language Models
  2. 2025Improving the Reliability of LLMs: Combining CoT, RAG, Self-Consistency, and Self-Verification
  3. 2025FActBench: A Benchmark for Fine-grained Automatic Evaluation of LLM-Generated Text in the Medical Domain
  4. 2026How Robust Is Multimodal Claim Verification to LLM Rewriting?
  5. 2026HALLMARK: How to Diagnose LLM Citation Verifiers and When to Deploy Them
  6. 2025Verifying the Verifiers: Unveiling Pitfalls and Potentials in Fact Verifiers
  7. 2024Abstention vs. Hallucination: Benchmarking LLM Source Attribution for Scientific Citations
  8. 2025Toward Reliable Scientific Hypothesis Generation: Evaluating Truthfulness and Hallucination in Large Language Models