Skip to main content
Computer Science > Computation and Language
arXiv:2401.00396 (cs)
[Submitted on 31 Dec 2023 (v1), last revised 17 May 2024 (this version, v2)]
RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Models
Cheng Niu, Yuanhao Wu, Juno Zhu, Siliang Xu, Kashun Shum, Randy Zhong, Juntong Song, Tong Zhang
View PDF
HTML (experimental)
Retrieval-augmented generation (RAG) has become a main technique for alleviating hallucinations in large language models (LLMs). Despite the integration of RAG, LLMs may still present unsupported or contradictory claims to the retrieved contents. In order to develop effective hallucination prevention strategies under RAG, it is important to create benchmark datasets that can measure the extent of hallucination. This paper presents RAGTruth, a corpus tailored for analyzing word-level hallucinations in various domains and tasks within the standard RAG frameworks for LLM applications. RAGTruth comprises nearly 18,000 naturally generated responses from diverse LLMs using RAG. These responses have undergone meticulous manual annotations at both the individual cases and word levels, incorporating evaluations of hallucination intensity. We not only benchmark hallucination frequencies across different LLMs, but also critically assess the effectiveness of several existing hallucination detection methodologies. Furthermore, we show that using a high-quality dataset such as RAGTruth, it is possible to finetune a relatively small LLM and achieve a competitive level of performance in hallucination detection when compared to the existing prompt-based approaches using state-of-the-art large language models such as GPT-4.
Subjects:	Computation and Language (cs.CL)
Cite as:	arXiv:2401.00396 [cs.CL]
 	(or arXiv:2401.00396v2 [cs.CL] for this version)
 	
https://doi.org/10.48550/arXiv.2401.00396
Focus to learn more
Submission history
From: Yuanhao Wu [view email]
[v1] Sun, 31 Dec 2023 04:43:45 UTC (7,284 KB)
[v2] Fri, 17 May 2024 06:29:31 UTC (8,095 KB)

Access Paper:
View PDFHTML (experimental)TeX Source
view license
Current browse context: cs.CL
< prev next >

newrecent2024-01
Change to browse by: cs
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Export BibTeX Citation
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Demos
Related Papers
About arXivLabs
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)
About
Help
Contact
Subscribe
Copyright
Privacy Policy
Web Accessibility Assistance

arXiv Operational Status