Tag: natural language processing
Browse our exclusive articles!
Efficient Active Testing of Large Language Models
Discover a novel active testing method using approximate Neyman allocation to improve evaluation accuracy and reduce costs for large language models.
Emergent Semantic Role Understanding in Language Models
Explore how language models develop semantic role understanding during pre-training and fine-tuning for improved NLP performance.
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.
AI Embeddings for Capturing Preferences in Decisions
Discover how AI embeddings focusing on preferences improve collective decision-making beyond semantic analysis in online voting and deliberation.
Translation Tax Complexity in Chinese Multilingual Benchmarks
Explore how translation tax varies in English-Chinese benchmarks, revealing model-family effects and item-specific impacts on score inflation.