works on
code correctness 1code generation 1hidden state analysis 1large language models 1linear probing 1

From the 1 of 1 linked paper with an AI index.

collaborators

1 paper

cs.LG2026

Code Correctness Is Linearly Decodable from LLM Hidden States Before Generation

Carlo Di Cicco

The paper shows that the hidden state of a large language model right before it starts generating code contains a linear signal that predicts whether the produced code will be corr…