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。

Delving into "Delve"

4 点作者 perfunctory8 个月前

1 comment

joegibbs8 个月前
My own guess as to why GPT overuses delve is that it’s an artefact of RLHF. When you’re training a model to respond as a chatbot rather than the next most probable token you’ve people marking responses as good&#x2F;bad. You’ve got some other criteria as well, like what sounds good.<p>What’s probably happened is that the “delve” responses sound better to the people doing RLHF, so they’re disproportionally included in the output.<p>It’s not just delve, there would be a whole list of overused words that you could find by comparing a large corpus of GPT output (or any LLM) to a large corpus of human-written text. You could use that as heuristic for an AI detector, only problem being that you’d need a different corpus for each LLM.