Search papers, labs, and topics across Lattice.
The authors critically examine the claims made by Nastase et al. regarding the alignment between large language models (LLMs) and human brain language processing, arguing that while representational alignment can inform mechanistic hypotheses, it does not definitively identify the underlying mechanisms. They highlight the tension between asserting shared computational principles and acknowledging that alignment alone does not imply a common architecture or algorithm. The paper ultimately raises concerns about logical, causal, and computational underdetermination in the conclusions drawn about LLMs as mechanistic models of language.
LLM-brain alignment might suggest shared computational principles, but it fails to confirm a common underlying mechanism, revealing deeper issues of underdetermination in AI models.
Nastase et al. (2026) argue that large language models (LLMs) may illuminate language processing because both rely on distributed, context-sensitive representations shaped by statistical learning. Their rejection of simple cortical"boxology"is persuasive, and they articulate a strong case for the value of LLM-brain alignment research. The key question is what kind of inference LLM-brain alignment licenses. My claim here will be narrow: representational alignment can in principle constrain mechanistic hypotheses, but it does not by itself identify a mechanism. Nastase et al. acknowledge that an encoding model can capture features represented in neural activity without establishing a shared architecture or algorithm. Yet the authors sometime move from alignment to"shared computational principles"and ultimately to LLMs as mechanistic models of natural language. Indeed, their methodological caveat that alignment does not establish a shared architecture or algorithm sits uneasily with their conclusion that LLMs might instantiate the same computational principles as biological brains and provide a"fully mechanistic model"of language. I discuss what I consider to be problems of logical, causal, and computational underdetermination in Nastase et al.'s (2026) proposal.
