AI Tools & Models HOTFeaturedAll
arXiv cs.AIScore60

Knowledge After Collapse: Context and Wording Shape Factual Accessibility in Language Models

Summary

After a language model accepts a false correction, the context and wording of the conversation determine whether it can still retrieve the right fact, and this paper systematically reveals that knowledge-collapse phenomenon.

Why this matters

Covers model · Relevant to this topic

Open original ↗

Source: arXiv cs.AI · arxiv.org

Topics

Related items