mlsanityData to 7 Oct 2026

NV-Retriever: Improving text embedding models with effective hard-negative mining

arXiv 2407.15831 ↗First posted 22 Jul 2024cs.IR cs.AIcited by 83

On the map: Retrieval-augmented generation → Generation and context integration

Abstract (arXiv)

Text embedding models have been popular for information retrieval applications such as semantic search and Question-Answering systems based on Retrieval-Augmented Generation (RAG). Those models are typically Transformer models that are fine-tuned with contrastive learning objectives. One of the challenging aspects of fine-tuning embedding models is the selection of high quality hard-negative passages for contrastive learning. In this paper we introduce a family of positive-aware mining methods that use the positive relevance score as an anchor for effective false negative removal, leading to faster training and more accurate retrieval models. We provide an ablation study on hard-negative mining methods over their configurations, exploring different teacher and base models. We further demonstrate the efficacy of our proposed mining methods at scale with the NV-Retriever-v1 model, which scores 60.9 on MTEB Retrieval (BEIR) benchmark and placed 1st when it was published to the MTEB Retrieval on July, 2024.

Key facts. Cited by 83 papers in the map (data through 7 Oct 2026). Placed in Generation and context integration, one of 15 directions in Retrieval-augmented generation. Builds on 19 of its 35 references that are in the map. First posted on arXiv 22 Jul 2024.

Builds on

19 of 35 references.

Closest ancestors · 1

Same direction, newest first

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks22 May

Other references · 18

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  3. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  4. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  5. 2019HuggingFace's Transformers: State-of-the-art Natural Language Processingcited by 2,201
  6. 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,591
  7. 2018Know What You Don't Know: Unanswerable Questions for SQuADcited by 1,538
  8. 2021BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Modelscited by 1,225
  9. 2022Text Embeddings by Weakly-Supervised Contrastive Pre-trainingcited by 1,216
  10. 2020Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrievalcited by 846
  11. 2017Reading Wikipedia to Answer Open-Domain Questionscited by 777
  12. 2023Towards General Text Embeddings with Multi-stage Contrastive Learningcited by 705
6 more
  1. 2020RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answeringcited by 410
  2. 2020MiniLMv2: Multi-Head Self-Attention Relation Distillation for Compressing Pretrained Transformerscited by 240
  3. 2021RocketQAv2: A Joint Training Method for Dense Passage Retrieval and Passage Re-rankingcited by 175
  4. 2020Answering Complex Open-Domain Questions with Multi-Hop Dense Retrievalcited by 160
  5. 2024Arctic-Embed: Scalable, Efficient, and Accurate Text Embedding Modelscited by 60
  6. 2021Transformers with multi-modal features and post-fusion context for e-commerce session-based recommendationcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 15; 2025: 46; 2026: 22.

83 papers.

Sort:

By area:

  1. 2024MM-Embed: Universal Multimodal Retrieval with Multimodal LLMscited by 159
  2. 2025EmbeddingGemma: Powerful and Lightweight Text Representationscited by 128
  3. 2025VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learningcited by 68
  4. 2024Arctic-Embed 2.0: Multilingual Retrieval Without Compromisecited by 57
  5. 2025Llama-Embed-Nemotron-8B: A Universal Text Embedding Model for Multilingual and Cross-Lingual Taskscited by 46
  6. 2025GFM-RAG: Graph Foundation Model for Retrieval Augmented Generationcited by 40
  7. 2024Promptriever: Instruction-Trained Retrievers Can Be Prompted Like Language Modelscited by 39
  8. 2024CoRNStack: High-Quality Contrastive Data for Better Code Retrieval and Rerankingcited by 37
  9. 2024CodeXEmbed: A Generalist Embedding Model Family for Multiligual and Multi-task Code Retrievalcited by 33
  10. 2024LLMs are Also Effective Embedding Models: An In-depth Overviewcited by 32
  11. 2025Training Sparse Mixture Of Experts Text Embedding Modelscited by 32
  12. 2025The Distracting Effect: Understanding Irrelevant Passages in RAGcited by 32
38 more
  1. 2025Breaking the Batch Barrier (B3) of Contrastive Learning via Smart Batch Miningcited by 27
  2. 2024OCR Hinders RAG: Evaluating the Cascading Impact of OCR on Retrieval-Augmented Generationcited by 24
  3. 2025Llama Nemoretriever Colembed: Top-Performing Text-Image Retrieval Modelcited by 24
  4. 2025CoLLM: A Large Language Model for Composed Image Retrievalcited by 21
  5. 2025SweRank: Software Issue Localization with Code Rankingcited by 20
  6. 2025Hard Negatives, Hard Lessons: Revisiting Training Data Quality for Robust Information Retrieval with LLMscited by 17
  7. 2024Enhancing Q&A Text Retrieval with Ranking Models: Benchmarking, fine-tuning and deploying Rerankers for RAGcited by 16
  8. 2024Conan-embedding: General Text Embedding with More and Better Negative Samplescited by 15
  9. 2025ReasonEmbed: Enhanced Text Embeddings for Reasoning-Intensive Document Retrievalcited by 15
  10. 2025Hard Negative Mining for Domain-Specific Retrieval in Enterprise Systemscited by 14
  11. 2024Bridging Relevance and Reasoning: Rationale Distillation in Retrieval-Augmented Generationcited by 13
  12. 2025HarmMetric Eval: Benchmarking Metrics and Judges for LLM Harmfulness Assessmentcited by 12
  13. 2025Redundancy, Isotropy, and Intrinsic Dimensionality of Prompt-based Text Embeddingscited by 10
  14. 2025Position: Text Embeddings Should Capture Implicit Semantics, Not Just Surface Meaningcited by 10
  15. 2025Omni-Embed-Nemotron: A Unified Multimodal Retrieval Model for Text, Image, Audio, and Videocited by 10
  16. 2025Towards Better Instruction Following Retrieval Modelscited by 9
  17. 2025DocReRank: Single-Page Hard Negative Query Generation for Training Multi-Modal RAG Rerankerscited by 9
  18. 2025Model Generalization on Text Attribute Graphs: Principles with Large Language Modelscited by 8
  19. 2025SitEmb-v1.5: Improved Context-Aware Dense Retrieval for Semantic Association and Long Story Comprehensioncited by 8
  20. 2026Nemotron ColEmbed V2: Top-Performing Late Interaction Embedding Models for Visual Document Retrievalcited by 8
  21. 2024Reward-RAG: Enhancing RAG with Reward Driven Supervisioncited by 7
  22. 2025mFollowIR: a Multilingual Benchmark for Instruction Following in Retrievalcited by 7
  23. 2025Optimizing Case-Based Reasoning System for Functional Test Script Generation with Large Language Modelscited by 7
  24. 2025Retro-Rank-In: A Ranking-Based Approach for Inorganic Materials Synthesis Planningcited by 5
  25. 2025Unleashing the Power of LLMs in Dense Retrieval with Query Likelihood Modelingcited by 5
  26. 2025FamilyTool: A Multi-hop Personalized Tool Use Benchmarkcited by 5
  27. 2025MTEB-NL and E5-NL: Embedding Benchmark and Models for Dutchcited by 5
  28. 2026CSRv2: Unlocking Ultra-Sparse Embeddingscited by 5
  29. 2026Learning Retrieval Models with Sparse Autoencoderscited by 5
  30. 2024Understanding the Role of LLMs in Multimodal Evaluation Benchmarkscited by 4
  31. 2025ConFit v2: Improving Resume-Job Matching using Hypothetical Resume Embedding and Runner-Up Hard-Negative Miningcited by 4
  32. 2025Beyond Contrastive Learning: Synthetic Data Enables List-wise Training with Multiple Levels of Relevancecited by 4
  33. 2025Conan-Embedding-v2: Training an LLM from Scratch for Text Embeddingscited by 4
  34. 2026VeRVE: Versatile Retrieval for Videos via Unified Embeddingscited by 4
  35. 2025DIVE: Diversified Iterative Self-Improvementcited by 3
  36. 2025Generative AI Enhanced Financial Risk Management Information Retrievalcited by 3
  37. 2025CPRet: A Dataset, Benchmark, and Model for Retrieval in Competitive Programmingcited by 3
  38. 2025LGAI-EMBEDDING-Preview Technical Reportcited by 3

50 most cited of 83 All 83 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Enhancing Retrieval Performance: An Ensemble Approach For Hard Negative Mining
  2. 2026Training Dense Retrievers with Multiple Positive Passages
  3. 2025Improve Multi-Modal Embedding Learning via Explicit Hard Negative Gradient Amplifying
  4. 2025ELITE: Embedding-Less retrieval with Iterative Text Exploration
  5. 2024Beyond Benchmarks: Evaluating Embedding Model Similarity for Retrieval Augmented Generation Systems
  6. 2024Efficient fine-tuning methodology of text embedding models for information retrieval: contrastive learning penalty (clp)
  7. 2024Recent advances in text embedding: A Comprehensive Review of Top-Performing Methods on the MTEB Benchmark
  8. 2026DEO: Training-Free Direct Embedding Optimization for Negation-Aware Retrieval