The study investigates whether large language models (LLMs) develop internal representations similar to cognitive maps used by animals for flexible behavior. Using relational reasoning tasks and causal mosaic experiments, the authors found that LLMs beyond ten billion parameters can infer unstated relationships, generalize to synthetic entity names, and form abstract relational structures that combine with entity identities. These relational representations are stored as pairwise links and composed retrospectively, mediated by a sparse, distributed key‑value system that can be perturbed to implant false memories and alter behavior predictably.
arXiv:2611.13270v1 Announce Type: new Abstract: Recent work has identified a set of emergent symbolic mechanisms that support abstract reasoning in large language models, but it remains unclear what...
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.
The paper introduces DisCo, a framework that uses large language models (LLMs) to automatically generate interpretable symbolic cognitive models. DisCo employs evolutionary search guided by two structural components: a Validator that filters out structurally invalid models and a Cleaner that enhances parameter identifiability by removing redundancies. Experiments on three behavioral tasks show that DisCo produces models with performance comparable to task‑specific baselines, and ablation studies highlight the Validator’s role in maintaining psychologically meaningful structure.
arXiv:2605. 09159v2 Announce Type: replace Abstract: Recent work shows that large language models (LLMs) encode behavioral traits ("personas") as linear directions in activation space, often called "persona vectors".
arXiv:2611.00387v1 Announce Type: cross Abstract: Humans possess a remarkable ability to draw inferences from limited data. While some inferences are made intuitively from past experience, others req...
arXiv:2608. 02807v1 Announce Type: cross Abstract: How can we better represent the impact of sociocultural structures on decision making in computational cognitive models?
arXiv:2510.01030v2 Announce Type: replace Abstract: The human ability to translate diverse perceptual and linguistic inputs into structured behavior has been thought to rest on learning robust repres...
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.
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:2607. 22575v1 Announce Type: new Abstract: Human episodic memory supports the retrieval of experiences that unfold over extended timescales, yet the computational mechanisms underlying this ability remain debated due to the limited mechanistic accessibility in long-term memory experiments in humans.
arXiv:2609.35599v2 Announce Type: replace Abstract: When recalling lists of concepts (e.g., animals) during the semantic fluency task (SFT), both humans and large language models (LLMs) organise thei...
arXiv:2605.05593v2 Announce Type: replace Abstract: Despite the remarkable success of Multimodal Large Language Models (MLLMs) across diverse tasks, the internal mechanisms governing how they encode...