7 stories tagged Cognitive Science
A new study from UC Berkeley and Stanford reveals that large language models naturally develop specialized, brain-like modules for language, reasoning, and social cognition. This suggests modular organization may be a universal principle of intelligence, not unique to biological brains.
Researchers from ArXiv cs.CL discovered how language models distinguish between a character's belief and objective reality. The mechanism relies on a shared value slot that binds the attributed value and a router at the query position that selects which frame—belief or reality—to read from. This finding explains how AI handles nuanced, belief-based reasoning.
Researchers created a new AI model called the Cognitive Categorical Transformer (CCT) that mimics how the human brain categorizes information. It outperforms a standard model by 12% on a language test, showing promise for smarter, more context-aware AI assistants.
Researchers proposed a two-dimensional system to categorize AI agents. It considers both how they process information and what tasks they perform, helping designers build better tools. This could make AI systems more reliable and easier to understand.
Researchers have proposed a new framework to unify how AI agents remember information, bridging the gap between computer engineering and cognitive science. This could lead to smarter, more reliable AI assistants in the future.
Researchers found that geometric relations between semantic features in LLMs' hidden states closely match human psychological associations. The study projects 360 words onto 32 semantic axes, showing high correlation with human ratings.
Researchers introduce the Cognitive Synergy Framework to improve humor generation in LLMs. The approach uses six cognitive personas to create humorous content, addressing the challenge of incongruity in standard training methods.