#social-cognition News & Analysis

3 articles tagged with #social-cognition. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

3 articles

AIBullisharXiv – CS AI · Apr 77/10

🧠

Readable Minds: Emergent Theory-of-Mind-Like Behavior in LLM Poker Agents

Research published on arXiv demonstrates that large language models playing poker can develop sophisticated Theory of Mind capabilities when equipped with persistent memory, progressing to advanced levels of opponent modeling and strategic deception. The study found memory is necessary and sufficient for this emergent behavior, while domain expertise enhances but doesn't gate ToM development.

🧠 GPT-4

AINeutralarXiv – CS AI · Mar 176/10

🧠

Dynamic Theory of Mind as a Temporal Memory Problem: Evidence from Large Language Models

Research reveals that Large Language Models struggle with dynamic Theory of Mind tasks, particularly tracking how others' beliefs change over time. While LLMs can infer current beliefs effectively, they fail to maintain and retrieve prior belief states after updates occur, showing patterns consistent with human cognitive biases.

AINeutralarXiv – CS AI · Mar 36/104

🧠

To Think or Not To Think, That is The Question for Large Reasoning Models in Theory of Mind Tasks

A research study of nine advanced Large Language Models reveals that Large Reasoning Models (LRMs) do not consistently outperform non-reasoning models on Theory of Mind tasks, which assess social cognition abilities. The study found that longer reasoning often hurts performance and models rely on shortcuts rather than genuine deduction, suggesting formal reasoning advances don't transfer to social reasoning tasks.