arXiv:2608. 02807v1 Announce Type: cross Abstract: How can we better represent the impact of sociocultural structures on decision making in computational cognitive models?
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.
The article reports that large language models can predict and collaboratively modulate human memory search during a semantic fluency task. By tracking and forecasting participants’ semantic retrieval patterns, the models outperform other humans in following these mental trajectories. This suggests that AI can serve as a cognitive tool to extend human abilities in open‑ended conceptual exploration and creative ideation.
The study investigates how large language models (LLMs) can assist humans in semantic memory search tasks. By using the semantic fluency task (SFT), the researchers evaluate whether LLMs can follow and enhance human mental trajectories during generative semantic retrieval. Results show that an LLM’s ability to track and predict human memory trajectories in this task surpasses that of other humans.
arXiv:2605. 28969v2 Announce Type: replace-cross Abstract: If an AI agent makes decisions on a person's behalf, those decisions must align with its user.
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.
The paper introduces CAPRI, a dataset of conversations designed to test whether large language models (LLMs) can adapt their responses to users’ cultural backgrounds. Experiments show that while LLMs can infer a user’s cultural context and recall relevant conventions, they frequently fail to apply this knowledge when generating answers unless explicitly prompted to do so. The study also finds that LLMs’ cultural adaptations improve as more cues are provided, yet their default priors are not culture‑neutral and sometimes reflect the model’s country of origin.
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.