人工智能2024 · 分享于 Hacker News
Detecting hallucinations in large language models using semantic entropy
探索《Detecting hallucinations in large language models using semantic entropy》的原文与 Hacker News 社区讨论，查看来源并加入阅读清单。
从论文，走向讨论
看看社区如何讨论这个想法。
来自 Hacker News 的原始讨论。不同的视角、疑问，以及值得继续思考的线索。
最多展示 100 条相关讨论。论文可能出现在评论中，并非原帖投稿内容。
在讨论中发现的引用
按 HN 条目顺序展示最近的 50 条引用来源。
Yloganfrederick ·
Notes on OpenAI's new o1 chain-of-thought models
699 赞同629 评论
YTomte ·
Detecting hallucinations in large language models using semantic entropy
254 赞同179 评论
Yemil_sorensen ·
AI hallucinations: Why LLMs make things up (and how to fix it)
196 赞同245 评论
Yglymor ·
Researchers describe how to tell if ChatGPT is confabulating
56 赞同38 评论
Ybreadwinner ·
The thrill of AI is fading – and Wall Street is getting clear-eyed about value
40 赞同52 评论
Ybikenaga ·
Researchers describe how to tell if ChatGPT is confabulating
5 赞同1 评论
Ythrowaway888abc ·
Detecting hallucinations in large language models using semantic entropy
5 赞同0 评论
Ycyberlimerence ·
Detecting hallucinations in large language models using semantic entropy
2 赞同0 评论
Ytaubek ·
Detecting hallucinations in large language models using semantic entropy
2 赞同0 评论
Yvinnyvichy ·
Detecting hallucinations in large language models using semantic entropy
1 赞同0 评论
Ysupai ·
Show HN: Sup AI, a confidence-weighted ensemble (52.15% on Humanity's Last Exam)
1 赞同3 评论