Tag: LLM evaluation
Browse our exclusive articles!
Automated AI Safety Policy Analysis Using Taxonomy & LLMs
Discover how taxonomy-driven LLMs automate the analysis and comparison of global AI safety policies, enhancing evaluation and governance.
User Turn Generation Reveals Interaction Awareness in LLMs
Discover how user turn generation probes interaction awareness in language models, uncovering deeper conversational understanding beyond assistant response...
GBQA Benchmark: Testing LLMs for Bug Detection in Games
Explore GBQA, a benchmark evaluating large language models' ability to detect software bugs in games, highlighting current AI challenges in QA engineering.
Are Frontier Models Essential for Verifying Math Proofs?
Explore if frontier AI models are necessary for accurate mathematical proof verification and how smaller models can match their performance.
XpertBench: Benchmarking Expert-Level AI Tasks with Rubrics
Discover XpertBench, a benchmark evaluating AI models on expert-level tasks across 80 domains using detailed rubrics and unbiased LLM judges.