BEIR

BEIR is a benchmark dataset used to evaluate the performance of information retrieval systems across various tasks by providing a diverse set of query-document pairs.

Papers using BEIR (6)

LLM2IR: simple unsupervised contrastive learning makes long-context LLM great retriever2026Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agents2023 · 26 citesHYRR: Hybrid Infused Reranking for Passage Retrieval2022 · 3 citesInstruction Distillation Makes Large Language Models Efficient Zero-shot Rankers2023 · 3 citesLLM-Augmented Retrieval: Enhancing Retrieval Models Through Language Models and Doc-Level Embedding2024 · 1 citesListT5: Listwise Reranking with Fusion-in-Decoder Improves Zero-shot Retrieval2024