Chain-of-Verification Reduces Hallucination in Large Language Models
Abstract
Generation of plausible yet incorrect factual information, termed hallucination, is an unsolved issue in large language models. We study the ability of language models to deliberate on the responses they give in order to correct their mistakes. We develop the Chain-of-Verification (CoVe) method whereby the model first (i) drafts an initial response; then (ii) plans verification questions to fact-check its draft; (iii) answers those questions independently so the answers are not biased by other responses; and (iv) generates its final verified response. In experiments, we show CoVe decreases hallucinations across a variety of tasks, from list-based questions from Wikidata, closed book MultiSpanQA and longform text generation.
Cite
Text
Dhuliawala et al. "Chain-of-Verification Reduces Hallucination in Large Language Models." ICLR 2024 Workshops: R2-FM, 2024.Markdown
[Dhuliawala et al. "Chain-of-Verification Reduces Hallucination in Large Language Models." ICLR 2024 Workshops: R2-FM, 2024.](https://mlanthology.org/iclrw/2024/dhuliawala2024iclrw-chainofverification/)BibTeX
@inproceedings{dhuliawala2024iclrw-chainofverification,
title = {{Chain-of-Verification Reduces Hallucination in Large Language Models}},
author = {Dhuliawala, Shehzaad and Komeili, Mojtaba and Xu, Jing and Raileanu, Roberta and Li, Xian and Celikyilmaz, Asli and Weston, Jason E},
booktitle = {ICLR 2024 Workshops: R2-FM},
year = {2024},
url = {https://mlanthology.org/iclrw/2024/dhuliawala2024iclrw-chainofverification/}
}