按年被提到
20232023 · 1 次2026
大模型与语言模型›大模型预训练与缩放·arXiv:2308.03188 · cs.CL

Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategies

Liangming Pan, Michael Saxon, Wenda Xu, Deepak Nathani, Xinyi Wang, William Yang Wang · 2023
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2023-08-09 · 最近 2024-01-22
2不同的人
2活跃月份
2讨论串
25被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Large language models (LLMs) have demonstrated remarkable performance across a wide array of NLP tasks. However, their efficacy is undermined by undesired and inconsistent behaviors, including hallucination, unfaithful reasoning, and toxic content. A promising approach to rectify these flaws is self-correction, where the LLM itself is prompted or guided to fix problems in its own output. Techniques leveraging automated feedback -- either produced by the LLM itself or some external system -- are of particular interest as they are a promising way to make LLM-based solutions more practical and deployable with minimal human feedback. This paper presents a comprehensive review of this emerging class of techniques. We analyze and taxonomize a wide array of recent work utilizing these strategies, including training-time, generation-time, and post-hoc correction. We also summarize the major applications of this strategy and conclude by discussing future directions and challenges.

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stonebraker · 2024-01

“Might also be worth scanning, Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategies https://arxiv.org/abs/2308.03188”

Self-Rewarding Language Models原评论 ↗
被提交为 story · 1 次