MTR-Suite offers an LLM-based auditor, a low-cost multi-agent synthesis pipeline using greedy traversal clustering, and a new general-domain benchmark with superior discriminative power for conversational retrieval.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
MTR-Suite: A Framework for Evaluating and Synthesizing Conversational Retrieval Benchmarks
MTR-Suite offers an LLM-based auditor, a low-cost multi-agent synthesis pipeline using greedy traversal clustering, and a new general-domain benchmark with superior discriminative power for conversational retrieval.