{"slug": "no-country-for-old-linguists-llm-brain-alignment-underdetermines-neural", "title": "No country for old linguists: LLM-brain alignment underdetermines neural computation", "summary": "A new arXiv preprint (2609.03160v1) argues that representational alignment between large language models (LLMs) and brain activity does not by itself identify a mechanism, challenging claims by Nastase et al. (2026) that LLMs can serve as fully mechanistic models of language. The author contends that alignment can constrain mechanistic hypotheses but suffers from logical, causal, and computational underdetermination, despite acknowledging the value of LLM-brain alignment research.", "body_md": "arXiv:2609.03160v1 Announce Type: new\nAbstract: 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.", "url": "https://wpnews.pro/news/no-country-for-old-linguists-llm-brain-alignment-underdetermines-neural", "canonical_source": "https://arxiv.org/abs/2609.03160", "published_at": "2026-09-04 04:00:00+00:00", "updated_at": "2026-09-04 04:22:38.117069+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-research"], "entities": ["arXiv", "Nastase et al."], "alternates": {"html": "https://wpnews.pro/news/no-country-for-old-linguists-llm-brain-alignment-underdetermines-neural", "markdown": "https://wpnews.pro/news/no-country-for-old-linguists-llm-brain-alignment-underdetermines-neural.md", "text": "https://wpnews.pro/news/no-country-for-old-linguists-llm-brain-alignment-underdetermines-neural.txt", "jsonld": "https://wpnews.pro/news/no-country-for-old-linguists-llm-brain-alignment-underdetermines-neural.jsonld"}}