No AI summary available for this article.
Why It Matters
LLMs are trained to generate natural language.
Provenance
Discovered via ArXiv and published by ArXiv.
Key Claims
Original description
LLMs are trained to generate natural language. However, various strands of evidence indicate that an LLM's externalized linguistic outputs and mechanistically-extracted linguistic features can be an unreliable lens for understanding internal model computation. We introduce the term ``linguistic illegibility'' to broadly refer to scenarios in which an LLM's externalized or mechanistically-probed language artifacts fail to represent how the model actually thinks. We argue that the specter of linguistic illegibility is unavoidable for LLMs whose internal computations are not directly expressed vi...
Discovered via ArXiv
Research papers and preprints from arXiv.
Publisher: arxiv.org
ID: http://arxiv.org/abs/2609.02852v1 · Indexed about 2 hours ago