Passage Re-ranking with BERT

2019/01/13 by Rodrigo Nogueira, Kyunghyun Cho, Nogueira, Rodrigo +1 · 80 citations
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Information Retrieval (cs.IR) #Machine Learning (cs.LG) #Multimodal Machine Learning Applications #Natural Language Processing Techniques #Topic Modeling

paper · pdf · doi:10.48550/arxiv.1901.04085

openalex publication_date 2019/01/13 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Recently, neural models pretrained on a language modeling task, such as ELMo (Peters et al., 2017), OpenAI GPT (Radford et al., 2018), and BERT (Devlin et al., 2018), have achieved impressive results on various natural language processing tasks such as question-answering and natural language inference. In this paper, we describe a simple re-implementation of BERT for query-based passage re-ranking. Our system is the state of the art on the TREC-CAR dataset and the top entry in the leaderboard of the MS MARCO passage retrieval task, outperforming the previous state of the art by 27% (relative) in MRR@10. The code to reproduce our results is available at https://github.com/nyu-dl/dl4marco-bert

Citations

• Adam: A Method for Stochastic Optimization
• Reading Wikipedia to Answer Open-Domain Questions

Cited by

• CORE: A Unified Cascaded Ordinal Relevance Estimation Framework for E-commerce Search
• From Unstructured Recall to Schema-Grounded Memory: Reliable AI Memory via Iterative, Schema-Aware Extraction
• Towards a Relevance Posterior in Neural Information Access
• The Case Against Generation for Retrieval: Discriminative Language Models as Effective Retrievers
• MPR-CiteG: Enhancing RAG with Multi-Portfolio Retrieval and Citation-Grounded Generation
• SourceMinds at CheckThat! 2026: NLI-Grounded Citation Auditing in a Multi-Agent Pipeline for Full Fact-Checking Article Generation
• JKO-RAG: Distributional Retrieval as Wasserstein Free-Energy Gradient Flow
• Learning to Retrieve with Weakened Labels: Robust Training under Label Noise
• VERAFI: Verified Agentic Financial Intelligence through Neurosymbolic Policy Generation
• Optimizing Generative Ranking Relevance via Reinforcement Learning in Xiaohongshu Search
• CourseTimeQA: A Lecture-Video Benchmark and a Latency-Constrained Cross-Modal Fusion Method for Timestamped QA
• Towards Improving Interpretability of Language Model Generation through a Structured Knowledge Discovery Approach
• What Drives Cross-lingual Ranking? Retrieval Approaches with Multilingual Language Models
• Rethinking Retrieval: From Traditional Retrieval Augmented Generation to Agentic and Non-Vector Reasoning Systems in the Financial Domain for Large Language Models
• CREST: Improving Interpretability and Effectiveness of Troubleshooting at Ericsson through Criterion-Specific Trouble Report Retrieval
• Incorporating Token Importance in Multi-Vector Retrieval
• RAGSmith: A Framework for Finding the Optimal Composition of Retrieval-Augmented Generation Methods Across Datasets
• QueStER: Query Specification for Generative keyword-based Retrieval
• Search Is Not Retrieval: Decoupling Semantic Matching from Contextual Assembly in RAG
• E-CARE: An Efficient LLM-based Commonsense-Augmented Framework for E-Commerce
• Vote-in-Context: Turning VLMs into Zero-Shot Rank Fusers
• Can Conversational AI Counsel for Change? A Theory-Driven Approach to Supporting Dietary Intentions in Ambivalent Individuals
• Traceable Drug Recommendation over Medical Knowledge Graphs
• SPIRE: Structure-Preserving Interpretable Retrieval of Evidence
• Metadata-Driven Retrieval-Augmented Generation for Financial Question Answering
• OG-Rank: Learning to Rank Fast and Slow with Uncertainty and Reward-Trend Guided Adaptive Exploration
• Hierarchical Semantic Retrieval with Cobweb
• Probing Latent Knowledge Conflict for Faithful Retrieval-Augmented Generation
• From Reasoning LLMs to BERT: A Two-Stage Distillation Framework for Search Relevance
• ZeroGR: A Generalizable and Scalable Framework for Zero-Shot Generative Retrieval
• TaoSR-AGRL: Adaptive Guided Reinforcement Learning Framework for E-commerce Search Relevance
• Text2Stories: Evaluating the Alignment Between Stakeholder Interviews and Generated User Stories
• Study on LLMs for Promptagator-Style Dense Retriever Training
• Scalable In-context Ranking with Generative Models
• Grounding Large Language Models in Clinical Evidence: A Retrieval-Augmented Generation System for Querying UK NICE Clinical Guidelines
• From Factoid Questions to Data Product Requests: Benchmarking Data Product Discovery over Tables and Text
• Directed Information γ-covering: An Information-Theoretic Framework for Context Engineering
• jina-reranker-v3: Last but Not Late Interaction for Listwise Document Reranking
• Beyond RAG vs. Long-Context: Learning Distraction-Aware Retrieval for Efficient Knowledge Grounding
• QuantMind: A Context-Engineering Based Knowledge Framework for Quantitative Finance
• CLAUSE: Agentic Neuro-Symbolic Knowledge Graph Reasoning via Dynamic Learnable Context Engineering
• From Backlog Items to Security Guidance: Towards Continuous Security Compliance
• ContextNest: Verifiable Context Governance for Autonomous AI Agent
• Enhancing Transformer-Based Rerankers with Synthetic Data and LLM-Based Supervision
• A multi-query, multimodal, receiver-augmented solution to extract contemporary cardiology guideline information using large language models
• The Role of Vocabularies in Learning Sparse Representations for Ranking
• Retrieval Capabilities of Large Language Models Scale with Pretraining FLOPs
• Modernizing Facebook Scoped Search: Keyword and Embedding Hybrid Retrieval with LLM Evaluation
• A Survey on Retrieval And Structuring Augmented Generation with Large Language Models
• SEDM: Scalable Self-Evolving Distributed Memory for Agents
• ViRanker: A BGE-M3 & Blockwise Parallel Transformer Cross-Encoder for Vietnamese Reranking
• An Iterative LLM Framework for SIBT utilizing RAG-based Adaptive Weight Optimization
• Query Expansion in the Age of Pre-trained and Large Language Models: A Comprehensive Survey
• How Good are LLM-based Rerankers? An Empirical Analysis of State-of-the-Art Reranking Models
• Beyond Sequential Reranking: Reranker-Guided Search Improves Reasoning Intensive Retrieval
• Seeing the Forest Through the Trees: Knowledge Retrieval for Streamlining Particle Physics Analysis
• Domain-Aware RAG: MoL-Enhanced RL for Efficient Training and Scalable Retrieval
• LLMs for estimating positional bias in logged interaction data
• Ember: No-Code Context Enrichment via Similarity-Based Keyless Joins
• IntenT5: Search Result Diversification using Causal Language Models
• You Only Compress Once: Towards Effective and Elastic BERT Compression via Exploit-Explore Stochastic Nature Gradient
• Fact or Facsimile? Evaluating the Factual Robustness of Modern Retrievers
• From Search to Reasoning: A Five-Level RAG Capability Framework for Enterprise Data
• TED: A Pretrained Unsupervised Summarization Model with Theme Modeling and Denoising
• MODE: Mixture of Document Experts for RAG
• Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval
• Context-Aware Sentence/Passage Term Importance Estimation For First Stage Retrieval
• SPLADE v2: Sparse Lexical and Expansion Model for Information Retrieval
• How Reliable are LLMs for Reasoning on the Re-ranking task?
• REALM: Recursive Relevance Modeling for LLM-based Document Re-Ranking
• Longformer for MS MARCO Document Re-ranking Task
• Cross-language Information Retrieval
• Improving Dense Passage Retrieval with Multiple Positive Passages
• Multi-Perspective Semantic Information Retrieval
• Synthesizing scientific literature with retrieval-augmented language models
• Hubness Reduction with Dual Bank Sinkhorn Normalization for Cross-Modal Retrieval
• ReMoMask: Retrieval-Augmented Masked Motion Generation
• Beyond English-Only Reading Comprehension: Experiments in Zero-Shot\n Multilingual Transfer for Bulgarian
• Bidirectional Likelihood Estimation with Multi-Modal Large Language Models for Text-Video Retrieval
• An In-depth Analysis of Passage-Level Label Transfer for Contextual Document Ranking

Related

• Exploiting Sentence-Level Representations for Passage Ranking
• Investigating the Successes and Failures of BERT for Passage Re-Ranking
• Understanding the Behaviors of BERT in Ranking
• Learning-to-Rank with BERT in TF-Ranking
• Fast Passage Re-ranking with Contextualized Exact Term Matching and Efficient Passage Expansion