按年被提到
20232023 · 1 次2026
大模型与语言模型›幻觉与语言模型局限·arXiv:2309.11495 · cs.CL

Chain-of-Verification Reduces Hallucination in Large Language Models

Shehzaad Dhuliawala, Mojtaba Komeili, Jing Xu, Roberta Raileanu, Xian Li, Asli Celikyilmaz, Jason Weston · 2023
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2023-10-14 · 最近 2024-01-08
2不同的人
2活跃月份
2讨论串
211被引(OpenAlex)
arXiv 摘要(候选层不写导读)

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.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论oshams · 2024-01

“It's purely based on the code and we force the LLM to cite the code it describes to cut back on hallucination. We are adding a self verification steps (like chain-of-verification / https://arxiv.org/abs/2309.11495) in Wiki V2.”

Show HN: Auto Wiki – Turn your codebase into a Wiki原评论 ↗
被提交为 story · 1 次