mlsanityData to 7 Oct 2026

Osiris: A Lightweight Open-Source Hallucination Detection System

arXiv 2505.04844 ↗First posted 7 May 2025cs.CLcited by 0

On the map: Retrieval-augmented generation → Hallucination detection in RAG

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.

Key facts. No citing papers in the map yet (data through 7 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.

Builds on

21 of 28 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretability15 Oct
  2. 2024Lynx: An Open Source Hallucination Evaluation Model11 Jul
  3. 2023RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Models31 Dec

Other references · 18

  1. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
  2. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,115
  3. 2024LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Modelscited by 1,442
  4. 2021MuSiQue: Multihop Questions via Single-hop Question Compositioncited by 893
  5. 2017Zero-Shot Relation Extraction via Reading Comprehensioncited by 425
  6. 2023Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergycited by 343
  7. 2019MLQA: Evaluating Cross-lingual Extractive Question Answeringcited by 339
  8. 2023Sources of Hallucination by Large Language Models on Inference Taskscited by 168
  9. 2019Compositional Questions Do Not Necessitate Multi-hop Reasoningcited by 87
  10. 2024Blended RAG: Improving RAG (Retriever-Augmented Generation) Accuracy with Semantic Search and Hybrid Query-Based Retrieverscited by 83
  11. 2024LLMs Will Always Hallucinate, and We Need to Live With Thiscited by 77
  12. 2019Avoiding Reasoning Shortcuts: Adversarial Evaluation, Training, and Model Development for Multi-Hop QAcited by 63
6 more
  1. 2024Context Embeddings for Efficient Answer Generation in RAGcited by 26
  2. 2025FactCG: Enhancing Fact Checkers with Graph-Based Multi-Hop Datacited by 14
  3. 2024Dense Passage Retrieval: Is it Retrieving?cited by 12
  4. 2023Keyword Augmented Retrieval: Novel framework for Information Retrieval integrated with speech interfacecited by 11
  5. 2024Seemingly Plausible Distractors in Multi-Hop Reasoning: Are Large Language Models Attentive Readers?cited by 10
  6. 2024HEAL: Hierarchical Embedding Alignment Loss for Improved Retrieval and Representation Learningcited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Luna: An Evaluation Foundation Model to Catch Language Model Hallucinations with High Accuracy and Low Cost
  2. 2025LUMINA: Detecting Hallucinations in RAG System with Context-Knowledge Signals
  3. 2026RAGognizer: Hallucination-Aware Fine-Tuning via Detection Head Integration
  4. 2025Bi'an: A Bilingual Benchmark and Model for Hallucination Detection in Retrieval-Augmented Generation
  5. 2025MetaRAG: Metamorphic Testing for Hallucination Detection in RAG Systems
  6. 2025The Semantic Illusion: Certified Limits of Embedding-Based Hallucination Detection in RAG Systems
  7. 2025InterpDetect: Interpretable Signals for Detecting Hallucinations in Retrieval-Augmented Generation
  8. 2025Probabilistic distances-based hallucination detection in LLMs with RAG