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

arXiv: https://arxiv.org/abs/2509.05741 · HTML: https://mlsanity.com/paper/2509.05741/

## 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.

## Placed in

- LLM reasoning / [Hallucination detection and mitigation](https://mlsanity.com/lr/hallucination-detection-and-mitigation/)

## Builds on (most cited first, 22 of 22)

- [Answering Complex Open-Domain Questions with Multi-Hop Dense Retrieval](https://mlsanity.com/paper/2009.12756/) (2020)
- [Structured Chain-of-Thought Prompting for Code Generation](https://mlsanity.com/paper/2305.06599/) (2023)
- [Visual In-Context Learning for Large Vision-Language Models](https://mlsanity.com/paper/2402.11574/) (2024)
- [Automatic Prompt Augmentation and Selection with Chain-of-Thought from Labeled Data](https://mlsanity.com/paper/2302.12822/) (2023)
- [Evaluating the Factual Consistency of Large Language Models Through News Summarization](https://mlsanity.com/paper/2211.08412/) (2022)
- [The Dawn After the Dark: An Empirical Study on Factuality Hallucination in Large Language Models](https://mlsanity.com/paper/2401.03205/) (2024)
- [Enhancing Code LLMs with Reinforcement Learning in Code Generation: A Survey](https://mlsanity.com/paper/2412.20367/) (2024)
- [Mitigating Large Language Model Hallucinations via Autonomous Knowledge Graph-based Retrofitting](https://mlsanity.com/paper/2311.13314/) (2023)
- [Large Language Models have Intrinsic Self-Correction Ability](https://mlsanity.com/paper/2406.15673/) (2024)
- [Improving Medical Large Vision-Language Models with Abnormal-Aware Feedback](https://mlsanity.com/paper/2501.01377/) (2025)
- [SCORE: Story Coherence and Retrieval Enhancement for AI Narratives](https://mlsanity.com/paper/2503.23512/) (2025)
- [Hyper-RAG: Combating LLM Hallucinations using Hypergraph-Driven Retrieval-Augmented Generation](https://mlsanity.com/paper/2504.08758/) (2025)
- [Cedille: A large autoregressive French language model](https://mlsanity.com/paper/2202.03371/) (2022)
- [Do Advanced Language Models Eliminate the Need for Prompt Engineering in Software Engineering?](https://mlsanity.com/paper/2411.02093/) (2024)
- [System Prompt Optimization with Meta-Learning](https://mlsanity.com/paper/2505.09666/) (2025)
- [Large Language Models as Software Components: A Taxonomy for LLM-Integrated Applications](https://mlsanity.com/paper/2406.10300/) (2024)
- [Uncertainty-Aware Fusion: An Ensemble Framework for Mitigating Hallucinations in Large Language Models](https://mlsanity.com/paper/2503.05757/) (2025)
- [Enhanced Visual SLAM for Collision-free Driving with Lightweight Autonomous Cars](https://mlsanity.com/paper/2408.11582/) (2024)
- [Zero-knowledge LLM hallucination detection and mitigation through fine-grained cross-model consistency](https://mlsanity.com/paper/2508.14314/) (2025)
- [Prompt Baking](https://mlsanity.com/paper/2409.13697/) (2024)
- [MultiHal: Multilingual Dataset for Knowledge-Graph Grounded Evaluation of LLM Hallucinations](https://mlsanity.com/paper/2505.14101/) (2025)
- [ResNetVLLM-2: Addressing ResNetVLLM's Multi-Modal Hallucinations](https://mlsanity.com/paper/2504.14429/) (2025)

## 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.