Tag: AI language models
Browse our exclusive articles!
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.
Estimating Tail Risks in Language Model Outputs Safely
Discover efficient methods to estimate rare harmful outputs in language models, improving safety with fewer samples and better risk prediction.
Execution Feedback Boosts 1-3B Code Generation Models
Discover how execution feedback outperforms complex pipelines in enhancing 1-3B parameter code generation models for better local code refinement.
7 Unconventional Ways to Use Language Models Today
Discover 7 innovative and unconventional applications of language models to boost creativity, learning, coding, mental health, and more.
Conformal Interpretability of Temporal Concepts in LLM Agents
Explore how conformal interpretability reveals temporal concept evolution in LLM agents, improving transparency and performance in decision-making tasks.