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。

Ask HN: Why GPT should be reminded of the connection between some topics?

1 点作者 wseqyrku2 个月前
Sometimes, LLMs need reminders about the link between related topics (e.g., A and B), even though this connection exists in their training data. I suspect that while A is often mentioned alongside B, the reverse is less common. Are there practical techniques to reinforce these connections?

暂无评论

暂无评论