# HalluGuard: Evidence-Grounded Small Reasoning Models to Mitigate Hallucinations in Retrieval-Augmented Generation

arXiv: https://arxiv.org/abs/2510.00880 · HTML: https://mlsanity.com/paper/2510.00880/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Hallucination detection and mitigation, one of 17 directions in LLM reasoning.
- Builds on 20 of its 52 references that are in the map.
- First posted on arXiv 1 Oct 2025.

## Placed in

- LLM reasoning / [Hallucination detection and mitigation](https://mlsanity.com/lr/hallucination-detection-and-mitigation/)
- Retrieval-augmented generation / [Hallucination detection in RAG](https://mlsanity.com/rag/hallucination-detection-in-rag/)

## Builds on (most cited first, 20 of 20)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [Textbooks Are All You Need](https://mlsanity.com/paper/2306.11644/) (2023)
- [Quantifying the Carbon Emissions of Machine Learning](https://mlsanity.com/paper/1910.09700/) (2019)
- [Is ChatGPT a Good NLG Evaluator? A Preliminary Study](https://mlsanity.com/paper/2303.04048/) (2023)
- [A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Models](https://mlsanity.com/paper/2401.01313/) (2024)
- [On LLMs-Driven Synthetic Data Generation, Curation, and Evaluation: A Survey](https://mlsanity.com/paper/2406.15126/) (2024)
- [Does Prompt Formatting Have Any Impact on LLM Performance?](https://mlsanity.com/paper/2411.10541/) (2024)
- [Factcheck-Bench: Fine-Grained Evaluation Benchmark for Automatic Fact-checkers](https://mlsanity.com/paper/2311.09000/) (2023)
- [A Chain-of-Thought Is as Strong as Its Weakest Link: A Benchmark for Verifiers of Reasoning Chains](https://mlsanity.com/paper/2402.00559/) (2024)
- [Lynx: An Open Source Hallucination Evaluation Model](https://mlsanity.com/paper/2407.08488/) (2024)
- [Understanding Retrieval Augmentation for Long-Form Question Answering](https://mlsanity.com/paper/2310.12150/) (2023)
- [Generating Faithful Synthetic Data with Large Language Models: A Case Study in Computational Social Science](https://mlsanity.com/paper/2305.15041/) (2023)
- [Towards Trustworthy Retrieval Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2502.06872/) (2025)
- [Granite Guardian](https://mlsanity.com/paper/2412.07724/) (2024)
- [Fine Tuning without Catastrophic Forgetting via Selective Low Rank Adaptation](https://mlsanity.com/paper/2501.15377/) (2025)
- [A Short Survey on Small Reasoning Models: Training, Inference, Applications and Research Directions](https://mlsanity.com/paper/2504.09100/) (2025)
- [Teaching with Lies: Curriculum DPO on Synthetic Negatives for Hallucination Detection](https://mlsanity.com/paper/2505.17558/) (2025)

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

- [Detecting Hallucinations in Retrieval-Augmented Generation via Semantic-level Internal Reasoning Graph](https://mlsanity.com/paper/2601.03052/) (2026)
- [Twin Worlds: Equivariance-Based Abstention for Evidence-Grounded Reasoning](https://mlsanity.com/paper/2608.28018/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) excel in many NLP tasks but remain prone to hallucinations, limiting trust in real-world applications. We present HalluGuard, a 4B-parameter Small Reasoning Model (SRM) for mitigating hallucinations in Retrieval-Augmented Generation (RAG). HalluGuard classifies document-claim pairs as grounded or hallucinated and produces evidence-grounded justifications for transparency. Our approach combines (i) a domain-agnostic synthetic dataset derived from FineWeb and refined through multi-stage curation and data reformation, (ii) synthetic grounded and hallucinated claims, and (iii) preference-based fine-tuning with Odds Ratio Preference Optimization to distill large-model reasoning into a smaller backbone. On the RAGTruth subset of the LLM-AggreFact benchmark, HalluGuard achieves 84.0% balanced accuracy (BAcc), rivaling specialized models, MiniCheck (7B; 84.0%) and Granite Guardian 3.3 (8B; 82.2%) while using roughly half their parameters. Over the full benchmark it reaches 75.7% BAcc, matching larger general-purpose LLMs such as GPT-4o (75.9%). We will release HalluGuard and datasets under Apache 2.0 upon acceptance.