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。

Estimating the quality of academic books from their descriptions with ChatGPT

2 点作者 Jimmc4143 个月前

1 comment

Jimmc4143 个月前
from the paper:<p>high chatGPT scores on the descriptions are generally correlated with high citation counts (which the paper uses as ground truth for quality)<p>despite being part of the training criteria, novelty claims in book descriptions don&#x27;t lead to higher chatGPT scores, but they do correlate with higher citation counts.<p>books with indirect writing styles (&quot;the author shows&quot;) in the descriptions tend to get lower scores.