paper-with-me

Papers

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

2024-07-22 · Gabriel de Souza P. Moreira, Radek Osmulski, Mengyao Xu, Ronay Ak, Benedikt Schifferer, Even Oldridge

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. Many papers introduced new embedding model architectures and training approaches, however, one of the key ingredients, the process of mining negative passages, remains poorly explored or described. 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 propose a family of positive-aware mining methods that leverage the positive relevance score for more effective false negatives removal. We also provide a comprehensive ablation study on hard-negative mining methods over their configurations, exploring different teacher and base models. We demonstrate the efficacy of our proposed methods by introducing the NV-Retriever-v1 model, which scores 60.9 on MTEB Retrieval (BEIR) benchmark and 0.65 points higher than previous methods. The model placed 1st when it was published to MTEB Retrieval on July 07, 2024.

📄 PDF Abstract BibTeX arXiv:2407.15831

Code (0)

등록된 구현이 없습니다.

Tasks

Contrastive LearningInformation RetrievalQuestion AnsweringRAGRetrievalRetrieval-augmented Generation

Methods 이 논문이 사용한 방법론

Attention 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Position-Wise Feed-Forward Layer 설명 없음
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…

Similar Papers 제목 키워드 기반

BiCA: Effective Biomedical Dense Retrieval with Citation-Aware Hard Negatives

2025-11-11 · Aarush Sinha, Pavan Kumar S, Roshan Balaji, Nirav Pravinbhai Bhatt arxiv

Hard negatives are essential for training effective retrieval models. Hard-negative mining typically relies on ranking documents using cross-encoders or static embedding models based on similarity metrics such as cosine …

Domain Adaptation

Towards Robust Ranker for Text Retrieval

2022-06-16 · Yucheng Zhou, Tao Shen, Xiubo Geng, Chongyang Tao 외

A ranker plays an indispensable role in the de facto 'retrieval & rerank' pipeline, but its training still lags behind -- learning from moderate negatives or/and serving as an auxiliary module for a retriever. In this wo…

Passage RetrievalRerankingRetrievalText Retrieval

Mistral-SPLADE: LLMs for better Learned Sparse Retrieval

2024-08-20 · Meet Doshi, Vishwajeet Kumar, Rudra Murthy, Vignesh P 외

Learned Sparse Retrievers (LSR) have evolved into an effective retrieval strategy that can bridge the gap between traditional keyword-based sparse retrievers and embedding-based dense retrievers. At its core, learned spa…

DecoderLanguage ModelingLanguage ModellingLarge Language Model+3

Gecko: Versatile Text Embeddings Distilled from Large Language Models

2024-03-29 · Jinhyuk Lee, Zhuyun Dai, Xiaoqi Ren, Blair Chen 외

We present Gecko, a compact and versatile text embedding model. Gecko achieves strong retrieval performance by leveraging a key idea: distilling knowledge from large language models (LLMs) into a retriever. Our two-step …

Retrieval

Open Domain Question Answering over Tables via Dense Retrieval

2021-03-22 · NAACL 2021 4 · Jonathan Herzig, Thomas Müller, Syrine Krichene, Julian Martin Eisenschlos

Recent advances in open-domain QA have led to strong models based on dense retrieval, but only focused on retrieving textual passages. In this work, we tackle open-domain QA over tables for the first time, and show that …

Natural QuestionsOpen-Domain Question AnsweringQuestion AnsweringRetrieval