TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

WikiCrow: An article for every human gene

2 点作者 mskar8 个月前

1 comment

mskar8 个月前
We used an open-source AI RAG library, PaperQA2 (<a href="https:&#x2F;&#x2F;github.com&#x2F;Future-House&#x2F;paper-qa">https:&#x2F;&#x2F;github.com&#x2F;Future-House&#x2F;paper-qa</a>), to generate well cited articles for every gene in the human genome, ~15k of which had no existing prior articles. In terms of factuality, we tested our generated claims against the same gene&#x27;s human written Wikipedia article in a blinded study evaluated by PhD biologists. Our system&#x27;s articles were more precise on average than cited claims from existing articles. (<a href="https:&#x2F;&#x2F;paper.wikicrow.ai" rel="nofollow">https:&#x2F;&#x2F;paper.wikicrow.ai</a>)<p>The system is scalable in that we can comfortably generate all 19.2k gene articles once per week, building a repository of cited articles that automatically syncs with all published literature.