The paper presents a network-based framework that links cognitive skills, LLM architectures, and datasets to uncover the cognitive patterns of Large Language Models. It identifies module communities within LLMs that exhibit skill distributions partially mirroring distributed cognitive organization seen in avian and small mammalian brains, yet distinct from the focalized specialization of specific biological systems. The study highlights that LLM skill acquisition benefits from dynamic, cross-regional interactions and neural plasticity, suggesting fine-tuning should leverage distributed learning dynamics rather than rigid modular interventions.
arXiv:2608. 13567v1 Announce Type: new Abstract: The human brain exhibits a striking degree of functional specialization, with distinct networks supporting language, formal reasoning, reasoning about other minds, and reasoning about the physical world.
The paper introduces BioGlyph, a method that translates network topology into a language of structural roles such as hubs, community cores, and cross-community connectors. By encoding these roles in a universal, interpretable vocabulary, BioGlyph allows large language models to answer structural reasoning questions about networks more accurately—improving system accuracy by up to 26 percentage points compared to edge-based or numerical representations. Experiments across twenty networks in five domains show the approach is especially effective for dense, community-structured networks and reveals biologically meaningful patterns in a budding-yeast protein-interaction network.
arXiv:2607. 00397v1 Announce Type: cross Abstract: Understanding how complex cognitive functions are organized within artificial systems is central to interpreting large language models (LLMs) and relating them to biological cognition.
arXiv:2609.01170v1 Announce Type: new Abstract: Large language models exhibit a modular internal organization that mirrors well-studied functional networks of the human brain, but how this organizati...
arXiv:2507. 10005v2 Announce Type: replace Abstract: In recent years, graph-based machine learning techniques, such as reinforcement learning and graph neural networks, have garnered significant attention.
The study investigates whether language models tailored to specific cognitive domains better align with corresponding brain systems. By prompting and fine‑tuning large language models into six domain experts—sensory, spatial, numerical, reasoning, social, and abstract—the authors find that each expert’s representations more closely match the brain region associated with its domain than other experts. This domain‑specific alignment holds across multiple base models and fMRI datasets, while overall prediction accuracy remains largely unchanged, indicating that regional alignment can be obscured when summarizing across the brain.
Emergent Abilities in Large Language Models: A Survey reviews how scaling LLMs leads to previously unseen capabilities such as advanced reasoning, in-context learning, coding, and problem-solving. The paper critically examines definitions, inconsistencies, and the conditions that foster these abilities, including scaling laws, task complexity, pre‑training loss, quantization, and prompting strategies. It also discusses the extension to Large Reasoning Models and highlights safety concerns like deception, manipulation, and reward hacking, calling for improved evaluation and governance.
arXiv:2608. 12377v1 Announce Type: cross Abstract: Brains and large language models (LLMs) are fundamentally different memory systems, but they can be compared through shared functional questions: where memory-related information is represented, how partial cues recover broader associations, how new information is written or updated, and how memory-related states can be perturbed.
arXiv:2607. 26179v1 Announce Type: cross Abstract: LLMs are widely regarded as alien intelligences, systems whose cognitive operations are fundamentally unlike our own.
arXiv:2606. 01189v1 Announce Type: new Abstract: We argue that the AI community is now ready to move beyond benchmarking and consolidate scattered efforts in model analysis into a systematic discipline, a direction we term Model Science.
arXiv:2602. 17229v2 Announce Type: replace Abstract: The black-box nature of Large Language Models necessitates novel evaluation frameworks that transcend surface-level performance metrics.
arXiv:2608.30498v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have shown remarkable success in STEM domains, where progress is often driven by vertical, step-by-step deduct...