Pith

open record

sign in

arxiv: 2407.15831 · v2 · pith:OFLWBQIJ · submitted 2024-07-22 · cs.IR · cs.AI

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

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 reserved pith:OFLWBQIJrecord.jsonopen to challenge →

classification cs.IR cs.AI
keywords modelsminingretrievalembeddinghard-negativemethodscontrastiveeffective
0
0 comments X
read the original abstract

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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 14 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. CATCH-ME if you RAG: a dataset of Contextually Annotated multi-Turn Counterspeech against Hate and Misinformation Exchanges

    cs.CL 2026-06 unverdicted novelty 8.0

    Presents a new expert-curated dataset of multi-turn counterspeech dialogues in five languages targeting hate against seven groups, with span annotations linking to verified external knowledge for RAG applications.

  2. Argus-Retriever: Vision-LLM Late-Interaction Retrieval with Region-Aware Query-Conditioned MoE for Visual Document Retrieval

    cs.IR 2026-06 unverdicted novelty 7.0

    Argus achieves the highest reported NDCG scores among open late-interaction models on ViDoRe V1 and combined V1+V2 by introducing query-dependent document representations via a region-aware MoE on Qwen3.5-VL, trained ...

  3. On the Robustness of LLM-Based Dense Retrievers: A Systematic Analysis of Generalizability and Stability

    cs.IR 2026-04 unverdicted novelty 7.0

    LLM-based dense retrievers generalize better when instruction-tuned but pay a specialization tax when optimized for reasoning; they resist typos and corpus poisoning better than encoder-only baselines yet remain vulne...

  4. vstash: Local-First Hybrid Retrieval with Adaptive Fusion for LLM Agents

    cs.IR 2026-04 conditional novelty 7.0

    vstash shows that hybrid retrieval disagreements provide a free training signal to fine-tune 33M-parameter embeddings, yielding NDCG@10 gains up to 19.5% on NFCorpus and matching some larger models on three of five BE...

  5. MemGraphRAG: Memory-based Multi-Agent System for Graph Retrieval-Augmented Generation

    cs.IR 2026-05 unverdicted novelty 6.0

    MemGraphRAG uses a memory-based multi-agent system for globally consistent graph construction from fragmented corpora plus a memory-aware hierarchical retriever, claiming better benchmark performance than prior GraphR...

  6. MLAIRE: Multilingual Language-Aware Information Retrieval Evaluation Protocal

    cs.IR 2026-05 unverdicted novelty 6.0

    MLAIRE is a protocol that evaluates multilingual retrievers on both semantic accuracy and query-language preference using parallel passages and new metrics like LPR and Lang-nDCG, showing that standard metrics hide di...

  7. ARHN: Answer-Centric Relabeling of Hard Negatives with Open-Source LLMs for Dense Retrieval

    cs.IR 2026-04 unverdicted novelty 6.0

    ARHN refines hard-negative training data for dense retrieval by using LLMs to convert answer-containing passages into additional positives and exclude answer-containing passages from the negative set.

  8. EmbeddingGemma: Powerful and Lightweight Text Representations

    cs.CL 2025-09 unverdicted novelty 6.0

    A 300M-parameter open embedding model sets new SOTA on MTEB for its size class and matches models twice as large while staying effective when compressed.

  9. SitEmb-v1.5: Improved Context-Aware Dense Retrieval for Semantic Association and Long Story Comprehension

    cs.CL 2025-08 unverdicted novelty 6.0

    SitEmb-v1.5 uses a new training paradigm to produce context-situated embeddings for short chunks, outperforming larger models by over 10% on a curated book-plot retrieval benchmark.

  10. NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models

    cs.CL 2024-05 accept novelty 6.0

    NV-Embed achieves first place on the MTEB leaderboard across 56 tasks by combining a latent attention layer, causal-mask removal, two-stage contrastive training, and data curation for LLM-based embedding models.

  11. Learn to Pool: Lightweight Fine-Tuning for Flexible Multi-Vector Compression

    cs.IR 2026-07 conditional novelty 5.0

    Lightweight pooling-aware fine-tuning with k-means on a single dataset enables up to 83% vector compression in ColBERT models with no retrieval accuracy loss and positive cross-dataset transfer.

  12. PRAGMA: Revolut Foundation Model

    cs.LG 2026-04 unverdicted novelty 5.0

    PRAGMA pre-trains a Transformer on heterogeneous banking events with a tailored self-supervised masked objective, yielding embeddings that support strong downstream performance on credit scoring, fraud detection, and ...

  13. Improving Korean-English Cross-Lingual Retrieval: A Data-Centric Study of Language Composition and Model Merging

    cs.IR 2025-07 unverdicted novelty 5.0

    Language composition in training data creates opposing effects on CLIR and mono-IR performance for Korean-English retrieval, which model merging can partially resolve.

  14. Negative Data Mining for Contrastive Learning in Dense Retrieval at IKEA.com

    cs.IR 2026-05 conditional novelty 3.0

    Structured negative mining with taxonomy and LLM judges improves offline category accuracy by 2.6% in IKEA search but yields no significant online engagement gains due to prevalent zero-click user behavior.