Get the latest tech news

Evaluating the factuality of verifiable claims in long-form text generation

Yixiao Song, Yekyung Kim, Mohit Iyyer. Findings of the Association for Computational Linguistics: EMNLP 2024. 2024.

We address this issue with VERISCORE,1 a metric for evaluating factuality in diverse long-form generation tasks that contain both verifiable and unverifiable content. Anthology ID: 2024.findings-emnlp.552 Volume: Findings of the Association for Computational Linguistics: EMNLP 2024 Month: November Year: 2024 Address: Miami, Florida, USA Editors: Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen Venue: Findings SIG:Publisher: Association for Computational Linguistics Note:Pages: 9447–9474 Language:URL: https://aclanthology.org/2024.findings-emnlp.552/ DOI: 10.18653/v1/2024.findings-emnlp.552 Bibkey: song-etal-2024-veriscore Cite (ACL): Yixiao Song, Yekyung Kim, and Mohit Iyyer. Cite (Informal): VeriScore: Evaluating the factuality of verifiable claims in long-form text generation(Song et al., Findings 2024) Copy Citation: BibTeXMarkdownMODS XMLEndnoteMore options… PDF: https://aclanthology.org/2024.findings-emnlp.552.pdf Software: 2024.findings-emnlp.552.software.zip

Get the Android app