Tag: LLM research
Browse our exclusive articles!
Theory of Mind vs Self-Attribution in Large Language Models
Explore how Theory of Mind and self-attributions differ in LLMs and the impact of safety fine-tuning on their socio-cognitive abilities.
Sparse Auto-Encoders and Holistic Meaning in LLMs
Explore how sparse auto-encoders challenge and enrich holistic views on meaning in large language models (LLMs) through latent feature analysis.
Diminishing Returns of Early-Exit Decoding in LLMs
Explore why early-exit decoding shows reduced effectiveness in modern large language models and what this means for future NLP research.
Limited Metacognition in Large Language Models Revealed
Discover new research showing limited metacognitive abilities in large language models, highlighting their unique cognitive processing and future AI implic...