Benchmark RadarAI BENCHMARK PROFILE
NQP-Bench
NQP-Bench is a dataset within the OnePred paper for evaluating next-query prediction in multi-turn conversations. It spans three diverse subsets and is used to compare OnePred against baselines.
- Released
- 2026-05-22
- Readiness
- Runnable
- Primary field
- General AI
Why it matters
Next-query prediction lacks dedicated benchmarks; NQP-Bench provides a testbed for this task, enabling evaluation of proactive conversational systems.
Motivation
Although large language model (LLM) conversational systems process millions of multi-turn dialogues daily, they remain fundamentally reactive: they respond only after the user types a query.
Primary resources
Benchmark Radar records only publicly supported details and links back to primary sources for verification.