paper-with-me

홈 › Papers

REFIND: Retrieval-Augmented Factuality Hallucination Detection in Large Language Models

2025-02-19 · Donggeon Lee, Hwanjo Yu

Hallucinations in large language model (LLM) outputs severely limit their reliability in knowledge-intensive tasks such as question answering. To address this challenge, we introduce REFIND (Retrieval-augmented Factuality hallucINation Detection), a novel framework that detects hallucinated spans within LLM outputs by directly leveraging retrieved documents. As part of the REFIND, we propose the Context Sensitivity Ratio (CSR), a novel metric that quantifies the sensitivity of LLM outputs to retrieved evidence. This innovative approach enables REFIND to efficiently and accurately detect hallucinations, setting it apart from existing methods. In the evaluation, REFIND demonstrated robustness across nine languages, including low-resource settings, and significantly outperformed baseline models, achieving superior IoU scores in identifying hallucinated spans. This work highlights the effectiveness of quantifying context sensitivity for hallucination detection, thereby paving the way for more reliable and trustworthy LLM applications across diverse languages.

📄 PDF Abstract BibTeX arXiv:2502.13622

Code (0)

등록된 구현이 없습니다.

Tasks

HallucinationLanguage ModelingLanguage ModellingLarge Language ModelQuestion AnsweringRetrievalSensitivity

Similar Papers 제목 키워드 기반

Fine-grained Hallucination Detection and Editing for Language Models

2024-01-12 · Abhika Mishra, Akari Asai, Vidhisha Balachandran, Yizhong Wang 외

Large language models (LMs) are prone to generate factual errors, which are often called hallucinations. In this paper, we introduce a comprehensive taxonomy of hallucinations and argue that hallucinations manifest in di…

HallucinationRetrieval

Detecting Hallucinations in Retrieval-Augmented Generation via Semantic-level Internal Reasoning Graph

2026-01-06 · Jianpeng Hu, Yanzeng Li, Jialun Zhong, Wenfa Qi 외 arxiv

The Retrieval-augmented generation (RAG) system based on Large language model (LLM) has made significant progress. It can effectively reduce factuality hallucinations, but faithfulness hallucinations still exist. Previou…

Toward Faithful Retrieval-Augmented Generation with Sparse Autoencoders

2025-12-09 · Guangzhi Xiong, Zhenghao He, Bohan Liu, Sanchit Sinha 외 arxiv

Retrieval-Augmented Generation (RAG) improves the factuality of large language models (LLMs) by grounding outputs in retrieved evidence, but faithfulness failures, where generations contradict or extend beyond the provid…

Finetune-RAG: Fine-Tuning Language Models to Resist Hallucination in Retrieval-Augmented Generation

2025-05-16 · Zhan Peng Lee, Andre Lin, Calvin Tan

Retrieval-Augmented Generation (RAG) has emerged as a powerful framework to improve factuality in large language models (LLMs) by grounding their outputs in retrieved documents. However, ensuring perfect retrieval of rel…

HallucinationRAGRetrievalRetrieval-augmented Generation

Train for Truth, Keep the Skills: Binary Retrieval-Augmented Reward Mitigates Hallucinations

2025-10-20 · Tong Chen, Akari Asai, Luke Zettlemoyer, Hannaneh Hajishirzi 외 arxiv

Language models often generate factually incorrect information unsupported by their training data, a phenomenon known as extrinsic hallucination. Existing mitigation approaches often degrade performance on open-ended gen…

Reinforcement LearningInstruction FollowingQuestion Answering