Original Summary

As these are all just language models, can somebody make a decente model that returns the answer and also &quot;the information used&quot; in the original prompt to arrive at the answer.<p>I saw some examples of using jev-like models to check if a file content is relevant to some query or not as &quot;is this code file related to feature X?&quot;. This is already interesting for reducing token usage, but it would be even better if you can have a &quot;mask&quot; over the input tokens that tells which tokens are relevant to the answer, maybe for already giving file line ranges in a tool call result.<p>Another nice variant is having returned multiple masks one per topic i.e. segmentation but for text.<p>I think this is already pretty doable with current model architectures and would be very useful, but maybe this needs a model fine-tuned specifically on this task to work well. Does anybody know about the current state of this?

  • 情报分类：综合情报
  • 分类依据：内容未命中明确的垂直分类规则，归入综合情报
  • 信息来源：Hacker News 新项目
  • 发布时间：2026/9/29 21:55:39