arXiv:2608. 08159v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly reported to exhibit human-like neural and cognitive signatures, including concept cells, mental number lines, and cognitive maps.
arXiv:2607. 25907v1 Announce Type: cross Abstract: Activation steering controls model behavior by editing internal activations at inference time.
arXiv:2608. 05224v1 Announce Type: new Abstract: Large language models fine-tuned on human behavioural data have emerged as general-purpose cognitive proxies, but the scale this requires, and whether these models process task structure or exploit statistical shortcuts, remain open questions.
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:2607. 29062v1 Announce Type: new Abstract: Model capabilities have improved in large part due to scaling chain of thought.
arXiv:2608. 05164v1 Announce Type: cross Abstract: Independently trained large language models may develop shared internal representations of semantic concepts despite architectural differences -- but whether this geometric similarity has functional consequences for cross-model behavioural control remains untested.
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:2609.23065v1 Announce Type: cross Abstract: Chain-of-thought (CoT) can sound plausible yet be unfaithful to the model's underlying reasoning. Most prior work probes CoT faithfulness through inp...
arXiv:2605.30381v2 Announce Type: replace-cross Abstract: When a language model is fine-tuned to produce systematically incorrect responses, does this training leave a structured, linearly recoverabl...
arXiv:2607. 12447v1 Announce Type: cross Abstract: Reliable confidence -- the probability that a model's own answer is correct -- is essential for the trustworthy deployment of language models.
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.
The study investigates the consistency and specificity of language model circuits across six tasks and five models, focusing on component-level (attention heads and MLP blocks) and neuron-level circuits. Component-level circuits are highly consistent and causally important but lack task specificity, as ablating a circuit for one task similarly harms performance on other tasks. Neuron-level circuits show higher task specificity but lower consistency, with overlap mainly between closely related tasks. The analysis of Llama‑3.2‑3B reveals that shared components are predominantly MLP blocks, while attention heads act as generic attention‑sink heads.
arXiv:2608. 01548v1 Announce Type: cross Abstract: Language can be viewed as a formalized subset of thought: a consequence-governed symbolic structure projected from wider situated cognition.