A Token-level Reference-free Hallucination Detection Benchmark for Free-form Text Generation
Tianyu Liu, Yizhe Zhang, Chris Brockett, Yi Mao, Zhifang Sui, Weizhu Chen, Bill Dolan
Abstract
Large pretrained generative models like GPT-3 often suffer from hallucinating non-existent or incorrect content, which undermines their potential merits in real applications. Existing work usually attempts to detect these hallucinations based on a corresponding oracle reference at a sentence or document level. However ground-truth references may not be readily available for many free-form text generation applications, and sentence- or document-level detection may fail to provide the fine-grained signals that would prevent fallacious content in real time. As a first step to addressing these issues, we propose a novel token-level, reference-free hallucination detection task and an associated annotated dataset named HaDeS (HAllucination DEtection dataSet). To create this dataset, we first perturb a large number of text segments extracted from English language Wikipedia, and then verify these with crowd-sourced annotations. To mitigate label imbalance during annotation, we utilize an iterative model-in-loop strategy. We conduct comprehensive data analyses and create multiple baseline models.- Anthology ID:
- 2022.acl-long.464
- Volume:
- Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- May
- Year:
- 2022
- Address:
- Dublin, Ireland
- Editors:
- Smaranda Muresan, Preslav Nakov, Aline Villavicencio
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 6723–6737
- Language:
- URL:
- https://aclanthology.org/2022.acl-long.464
- DOI:
- 10.18653/v1/2022.acl-long.464
- Cite (ACL):
- Tianyu Liu, Yizhe Zhang, Chris Brockett, Yi Mao, Zhifang Sui, Weizhu Chen, and Bill Dolan. 2022. A Token-level Reference-free Hallucination Detection Benchmark for Free-form Text Generation. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6723–6737, Dublin, Ireland. Association for Computational Linguistics.
- Cite (Informal):
- A Token-level Reference-free Hallucination Detection Benchmark for Free-form Text Generation (Liu et al., ACL 2022)
- PDF:
- https://preview.aclanthology.org/improve-issue-templates/2022.acl-long.464.pdf
- Code
- microsoft/HaDes + additional community code
- Data
- HaDes