作者位次 #3/4SIGIR 2026Oral· Information Retrieval (Reproducibility)
Lighting the Way for BRIGHT: Reproducible Baselines with Anserini, Pyserini, and RankLLM
Sahel Sharifymoghaddam · Yijun Ge · Raghav Vasudeva · Jimmy Lin
摘要
Retrieval benchmarks for large language models (LLMs) should reflect the long, reasoning-intensive queries typical of retrieval-augmented generation (RAG). We present a systematic study of BRIGHT, a reasoning-focused retrieval benchmark, along with strong, reproducible reference methods integrate...