BEIR

Dataset Card for BEIR Benchmark Dataset Summary BEIR is a heterogeneous benchmark that has been built from 18 diverse datasets representing 9 information retrieval tasks: Fact-checking: FEVER, Climate-FEVER, SciFact Question-Answering: NQ, HotpotQA, FiQA-2018 Bio-Medical IR: TREC-COVID, BioASQ, NFCorpus News Retrieval:

Papers using BEIR (25)

ProRank: Prompt Warmup via Reinforcement Learning for Small Language Models Reranking2025Enhancing Lexicon-Based Text Embeddings with Large Language Models2025 · 1 citesA Systematic Study of Pseudo-Relevance Feedback with LLMs2026RankSteer: Activation Steering for Pointwise LLM Ranking2026LLM-Confidence Reranker: A Training-Free Approach for Enhancing Retrieval-Augmented Generation Systems2026LLM2IR: simple unsupervised contrastive learning makes long-context LLM great retriever2026Making Large Language Models Efficient Dense Retrievers2025Contextual Relevance and Adaptive Sampling for LLM-Based Document Reranking2025Scalable In-context Ranking with Generative Models2025Doc2Query++: Topic-Coverage based Document Expansion and its Application to Dense Retrieval via Dual-Index Fusion2025ERank: Fusing Supervised Fine-Tuning and Reinforcement Learning for Effective and Efficient Text Reranking2025How Good are LLM-based Rerankers? An Empirical Analysis of State-of-the-Art Reranking Models2025DeAR: Dual-Stage Document Reranking with Reasoning Agents via LLM Distillation2025Retrieval Capabilities of Large Language Models Scale with Pretraining FLOPs2025Precise Zero-Shot Pointwise Ranking with LLMs through Post-Aggregated Global Context Information2025From Token to Action: State Machine Reasoning to Mitigate Overthinking in Information Retrieval2025AcuRank: Uncertainty-Aware Adaptive Computation for Listwise Reranking2025From Token to Action: State Machine Reasoning to Mitigate Overthinking in Information Retrieval2025Utility-Focused LLM Annotation for Retrieval and Retrieval-Augmented Generation2025Pseudo Relevance Feedback is Enough to Close the Gap Between Small and Large Dense Retrieval Models2025RankFlow: A Multi-Role Collaborative Reranking Workflow Utilizing Large Language Models2025Scaling Sparse and Dense Retrieval in Decoder-Only LLMs2025Matryoshka Re-Ranker: A Flexible Re-Ranking Architecture With Configurable Depth and Width2025JudgeRank: Leveraging Large Language Models for Reasoning-Intensive Reranking2024 · 3 citesSelf-Calibrated Listwise Reranking with Large Language Models2024