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

Fernando Gabriela García, Qiyang Shi, Zilin Feng
9/6/2025
cs.CL

No confident code implementation found for this paper.

Abstract

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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Improving the Reliability of LLMs: Combining CoT, RAG, Self-Consistency, and Self-Verification

88% match2025

VeriFact: Enhancing Long-Form Factuality Evaluation with Refined Fact Extraction and Reference Facts

86% match1 repo12025

Hallucination to Truth: A Review of Fact-Checking and Factuality Evaluation in Large Language Models

85% match2025

Fine-Grained Self-Endorsement Improves Factuality and Reasoning

85% match2024

Multi-Modal Fact-Verification Framework for Reducing Hallucinations in Large Language Models

85% match2025

Truth or Mirage? Towards End-to-End Factuality Evaluation with LLM-Oasis

84% match1 repo252024

Cite this paper

@article{garca2025enhancing,
  title  = {Enhancing Factual Accuracy and Citation Generation in LLMs via Multi-Stage Self-Verification},
  author = {Fernando Gabriela García and Qiyang Shi and Zilin Feng},
  year   = {2025},
  eprint = {2509.05741},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2509.05741v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2509.05741.svg)](https://codeofpaper.com/paper/2509.05741)

Discussion