Tag: AI research agent
Browse our exclusive articles!
Categorical Perception in LLMs at Digit-Count Boundaries
Explore how large language models show categorical perception at digit-count boundaries, revealing structural warping in hidden states across architectures...
Causal Concept Graphs Boost Multi-Step Reasoning in LLMs
Discover how Causal Concept Graphs improve multi-step reasoning in large language models by capturing causal relationships in latent space.
Digital Consciousness Model: Early AI Consciousness Insights
Explore initial findings of the Digital Consciousness Model assessing AI consciousness and implications for future AI development and ethics.
Verbal Confidence Limits in 3-9B Instruction-Tuned LLMs
Study reveals invalid verbal confidence in 3-9B parameter instruction-tuned LLMs, urging psychometric screening for reliable uncertainty estimation.
Background Temperature Reveals Hidden Randomness in LLMs
Discover how background temperature explains hidden randomness in large language models, improving reproducibility and evaluation.