AI Tools & Models HOTFeaturedAll
arXiv cs.AIScore65

LECAT: Measuring LLM Category Learning from Pretraining Data

Summary

This benchmark measures how LLMs acquire category knowledge from pre-training data, such as knowing airplanes are fast but broken ones are not.

Why this matters

Covers LLM · Relevant to this topic

Open original ↗

Source: arXiv cs.AI · arxiv.org

Topics

Related items