# Osiris: A Lightweight Open-Source Hallucination Detection System

arXiv: https://arxiv.org/abs/2505.04844 · HTML: https://mlsanity.com/paper/2505.04844/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Hallucination detection in RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 21 of its 28 references that are in the map.
- First posted on arXiv 7 May 2025.

## Placed in

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

## Builds on (most cited first, 21 of 21)

- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [MuSiQue: Multihop Questions via Single-hop Question Composition](https://mlsanity.com/paper/2108.00573/) (2021)
- [Zero-Shot Relation Extraction via Reading Comprehension](https://mlsanity.com/paper/1706.04115/) (2017)
- [Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergy](https://mlsanity.com/paper/2305.15294/) (2023)
- [MLQA: Evaluating Cross-lingual Extractive Question Answering](https://mlsanity.com/paper/1910.07475/) (2019)
- [RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Models](https://mlsanity.com/paper/2401.00396/) (2023)
- [Sources of Hallucination by Large Language Models on Inference Tasks](https://mlsanity.com/paper/2305.14552/) (2023)
- [ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretability](https://mlsanity.com/paper/2410.11414/) (2024)
- [Compositional Questions Do Not Necessitate Multi-hop Reasoning](https://mlsanity.com/paper/1906.02900/) (2019)
- [Blended RAG: Improving RAG (Retriever-Augmented Generation) Accuracy with Semantic Search and Hybrid Query-Based Retrievers](https://mlsanity.com/paper/2404.07220/) (2024)
- [LLMs Will Always Hallucinate, and We Need to Live With This](https://mlsanity.com/paper/2409.05746/) (2024)
- [Avoiding Reasoning Shortcuts: Adversarial Evaluation, Training, and Model Development for Multi-Hop QA](https://mlsanity.com/paper/1906.07132/) (2019)
- [Lynx: An Open Source Hallucination Evaluation Model](https://mlsanity.com/paper/2407.08488/) (2024)
- [Context Embeddings for Efficient Answer Generation in RAG](https://mlsanity.com/paper/2407.09252/) (2024)
- [FactCG: Enhancing Fact Checkers with Graph-Based Multi-Hop Data](https://mlsanity.com/paper/2501.17144/) (2025)
- [Dense Passage Retrieval: Is it Retrieving?](https://mlsanity.com/paper/2402.11035/) (2024)
- [Keyword Augmented Retrieval: Novel framework for Information Retrieval integrated with speech interface](https://mlsanity.com/paper/2310.04205/) (2023)
- [Seemingly Plausible Distractors in Multi-Hop Reasoning: Are Large Language Models Attentive Readers?](https://mlsanity.com/paper/2409.05197/) (2024)
- [HEAL: Hierarchical Embedding Alignment Loss for Improved Retrieval and Representation Learning](https://mlsanity.com/paper/2412.04661/) (2024)

## Abstract (arXiv)

Retrieval-Augmented Generation (RAG) systems have gained widespread adoption by application builders because they leverage sources of truth to enable Large Language Models (LLMs) to generate more factually sound responses. However, hallucinations, instances of LLM responses that are unfaithful to the provided context, often prevent these systems from being deployed in production environments. Current hallucination detection methods typically involve human evaluation or the use of closed-source models to review RAG system outputs for hallucinations. Both human evaluators and closed-source models suffer from scaling issues due to their high costs and slow inference speeds. In this work, we introduce a perturbed multi-hop QA dataset with induced hallucinations. Via supervised fine-tuning on our dataset, we achieve better recall with a 7B model than GPT-4o on the RAGTruth hallucination detection benchmark and offer competitive performance on precision and accuracy, all while using a fraction of the parameters. Code is released at our repository.