y0news
AnalyticsDigestsSourcesTopicsRSSAICrypto

#cognitive-research News & Analysis

4 articles tagged with #cognitive-research. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

4 articles
AINeutralarXiv – CS AI · Apr 77/10
🧠

The Persuasion Paradox: When LLM Explanations Fail to Improve Human-AI Team Performance

Research reveals a 'Persuasion Paradox' where LLM explanations increase user confidence but don't reliably improve human-AI team performance, and can actually undermine task accuracy. The study found that explanation effectiveness varies significantly by task type, with visual reasoning tasks seeing decreased error recovery while logical reasoning tasks benefited from explanations.

AIBearisharXiv – CS AI · Mar 26/1013
🧠

Humans and LLMs Diverge on Probabilistic Inferences

Researchers created ProbCOPA, a dataset testing probabilistic reasoning in humans versus AI models, finding that state-of-the-art LLMs consistently fail to match human judgment patterns. The study reveals fundamental differences in how humans and AI systems process non-deterministic inferences, highlighting limitations in current AI reasoning capabilities.

AINeutralarXiv – CS AI · Mar 274/10
🧠

Gaze patterns predict preference and confidence in pairwise AI image evaluation

Researchers used eye-tracking to analyze how humans make preference judgments when evaluating AI-generated images, finding that gaze patterns can predict both user choices and confidence levels. The study revealed that participants' eyes shift toward chosen images about one second before making decisions, and gaze features achieved 68% accuracy in predicting binary choices.

AINeutralarXiv – CS AI · Feb 274/108
🧠

Exploring Human Behavior During Abstract Rule Inference and Problem Solving with the Cognitive Abstraction and Reasoning Corpus

Researchers introduced CogARC, a human-adapted subset of the Abstraction and Reasoning Corpus, to study how humans solve abstract visual reasoning problems. In experiments with 260 participants solving 75 problems, researchers found high success rates (~80-90%) but significant variation in problem difficulty and solution strategies.