Tag: AI language models
Browse our exclusive articles!
Data-driven Circuit Discovery for Interpreting Language Models
Discover how Data-driven Circuit Discovery (DCD) enhances interpretability of language models by revealing multiple task-specific circuits.
Re$^2$Math: Benchmarking Theorem Retrieval in Math Research
Explore Re$^2$Math, a benchmark evaluating theorem retrieval in research-level mathematics using AI and language models for improved proof assistance.
Impossibility Theorems Reveal Bias in Sequential AI Processing
Discover how cognitive biases are inevitable in sequential AI and human validation, backed by new impossibility theorems and experimental proof.
Enhancing AI Decision-Making with Emotion Vectors in Language Models
Discover how emotion vector re-injection improves language models' decision-making by integrating emotional memory for better AI understanding.
Boost RL in Language Models with Self-Generated Data
Enhance reinforcement learning in language models by mid-training with diverse self-generated data for improved reasoning and problem-solving abilities.