AI Tools & Models HOTFeaturedAll
arXiv cs.AIScore65

WeightBench: Evaluating Language Models as Weight-Space Programmers

Summary

This benchmark tests whether language models can read and operate on other networks' parameters like programmers working with code.

Why this matters

Covers model and LLM · Relevant to this topic

Open original ↗

Source: arXiv cs.AI · arxiv.org

Topics

Related items