SeedRG generates novel, leakage-free RAG benchmark examples from seed data by mapping reasoning structures and swapping entities while applying consistency and leakage checks.
Benchmark leakage trap: Can we trust llm-based recommendation?arXiv preprint arXiv:2602.13626
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
-
Generating Leakage-Free Benchmarks for Robust RAG Evaluation
SeedRG generates novel, leakage-free RAG benchmark examples from seed data by mapping reasoning structures and swapping entities while applying consistency and leakage checks.