QA benchmarks

The 'QA benchmarks' are datasets used to evaluate the performance of agents in knowledge-intensive question answering tasks, specifically measuring their accuracy and efficiency in retrieving and reasoning with information.

Papers using QA benchmarks (4)

Grad Detect: Gradient-Based Hallucination Detection in LLMs2026When Can Conformal Risk Control Certify LLM Outputs? Bounds, Impossibility, and Adaptation for Structured Generation2026ModelLens: Finding the Best for Your Task from Myriads of Models2026CalVerT: Augmenting Agents with Calibrated Verifier Telemetry Improves Action and Learning in Knowledge-Intensive Tasks2026