Pratik Worah, Randall Bateman · 2026 · arXiv
DOI: 10.48550/arXiv.2610.28214 · open-access PDF
A perda neuronal progressiva é a marca distintiva da doença neurodegenerativa, mas como a perda de neurônios forma o padrão de declínio cognitivo permanece mal compreendido. Aqui nós sistematicamente abafamos neurônios (unidades computacionais) em modelos de linguagem que abrangem as arquiteturas de memória de curto prazo recorrente (LSTM) e transformador e aplicamos ajustes finos limitados como um simples proxy para a plasticidade compensatória. Com a ablação de unidade inteira, os LSTMs degradam gradualmente com as faculdades sintáticas e semânticas diminuindo em paralelo através de danos leves a moderados.
Machine translation (Meta M2M100); the English original follows.
Progressive neuronal loss is the hallmark of neurodegenerative disease, yet how loss of neurons shapes the pattern of cognitive decline remains poorly understood. Here we systematically ablate neurons (computational units) in language models spanning recurrent long short-term memory (LSTM) and Transformer architectures and apply limited fine-tuning as a simple proxy for compensatory plasticity. With whole-unit ablation, LSTMs degrade gradually with syntactic and semantic faculties declining in parallel across mild-to-moderate damage. By contrast, Transformers exhibit late threshold-like collap
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.28214, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange