Tag: AI Benchmarks
Browse our exclusive articles!
SLIDERS: Scalable QA with Structured Reasoning on Long Docs
Discover SLIDERS, a framework that improves question answering accuracy and scalability over long document sets using structured reasoning.
MuDABench: Benchmark for Multi-Document Analytical QA
Discover MuDABench, a new benchmark enhancing multi-document analytical QA for large-scale document collections in finance and law.
Math Takes Two: Benchmark for AI Mathematical Reasoning
Discover Math Takes Two, a new AI benchmark testing emergent mathematical reasoning through collaborative communication and visually grounded tasks.
Evaluating Generative AI as Pluralist Sociotechnical Systems
Explore a pluralist framework for evaluating generative AI, focusing on sociotechnical interactions, values, and responsible benchmarks beyond static measu...
SafetyALFRED: Testing Safety in Multimodal Language Models
Discover SafetyALFRED, a benchmark assessing safety-conscious planning of multimodal large language models in real-world hazard scenarios.