# HalluDetect: Detecting, Mitigating, and Benchmarking Hallucinations in Conversational Systems in the Legal Domain

arXiv: https://arxiv.org/abs/2509.11619 · HTML: https://mlsanity.com/paper/2509.11619/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 35 references that are in the map.
- First posted on arXiv 15 Sep 2025.

## Builds on (most cited first, 12 of 12)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://mlsanity.com/paper/2305.14251/) (2023)
- [CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing](https://mlsanity.com/paper/2305.11738/) (2023)
- [MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling](https://mlsanity.com/paper/1810.00278/) (2018)
- [Retrieval Augmentation Reduces Hallucination in Conversation](https://mlsanity.com/paper/2104.07567/) (2021)
- [FacTool: Factuality Detection in Generative AI -- A Tool Augmented Framework for Multi-Task and Multi-Domain Scenarios](https://mlsanity.com/paper/2307.13528/) (2023)
- [Complex Claim Verification with Evidence Retrieved in the Wild](https://mlsanity.com/paper/2305.11859/) (2023)
- [LettuceDetect: A Hallucination Detection Framework for RAG Applications](https://mlsanity.com/paper/2502.17125/) (2025)
- [Retrieving Supporting Evidence for LLMs Generated Answers](https://mlsanity.com/paper/2306.13781/) (2023)
- [Good Parenting is all you need -- Multi-agentic LLM Hallucination Mitigation](https://mlsanity.com/paper/2410.14262/) (2024)

## Abstract (arXiv)

Large Language Models (LLMs) are widely used in industry but remain prone to hallucinations, limiting their reliability in critical applications. This work addresses hallucination reduction in consumer grievance chatbots built using LLaMA 3.1 8B Instruct, a compact model frequently used in industry. We develop HalluDetect, an LLM-based hallucination detection system that achieves an F1 score of 68.92% outperforming baseline detectors by 22.47%. Benchmarking five hallucination mitigation architectures, we find that out of them, AgentBot minimizes hallucinations to 0.4159 per turn while maintaining the highest token accuracy (96.13%), making it the most effective mitigation strategy. Our findings provide a scalable framework for hallucination mitigation, demonstrating that optimized inference strategies can significantly improve factual accuracy.