paper-with-me

홈 › Papers

Search-Adaptor: Embedding Customization for Information Retrieval

2023-10-12 · Jinsung Yoon, Sercan O Arik, Yanfei Chen, Tomas Pfister

Embeddings extracted by pre-trained Large Language Models (LLMs) have significant potential to improve information retrieval and search. Beyond the zero-shot setup in which they are being conventionally used, being able to take advantage of the information from the relevant query-corpus paired data can further boost the LLM capabilities. In this paper, we propose a novel method, Search-Adaptor, for customizing LLMs for information retrieval in an efficient and robust way. Search-Adaptor modifies the embeddings generated by pre-trained LLMs, and can be integrated with any LLM, including those only available via prediction APIs. On multiple English, multilingual, and multimodal retrieval datasets, we show consistent and significant performance benefits for Search-Adaptor -- e.g., more than 5% improvements for Google Embedding APIs in nDCG@10 averaged over 14 BEIR datasets.

📄 PDF Abstract BibTeX arXiv:2310.08750

Code (0)

등록된 구현이 없습니다.

Tasks

Information RetrievalRetrieval

Similar Papers 제목 키워드 기반

SMEC: Rethinking Matryoshka Representation Learning for Retrieval Embedding Compression

2025-10-14 · Biao Zhang, Lixin Chen, Tong Liu, Bo Zheng arxiv

Large language models (LLMs) generate high-dimensional embeddings that capture rich semantic and syntactic information. However, high-dimensional embeddings exacerbate computational complexity and storage requirements, t…

Dimensionality ReductionRepresentation Learning

NUDGE: Lightweight Non-Parametric Fine-Tuning of Embeddings for Retrieval

2024-09-04 · Sepanta Zeighami, Zac Wellmer, Aditya Parameswaran

$k$-Nearest Neighbor search on dense vector embeddings ($k$-NN retrieval) from pre-trained embedding models is the predominant retrieval method for text and images, as well as Retrieval-Augmented Generation (RAG) pipelin…

Image RetrievalRAGRetrievalRetrieval-augmented Generation

DIVE: Embedding Compression via Self-Limiting Gradient Updates

2026-05-20 · Dongfang Zhao arxiv

High-dimensional embeddings from large language models impose significant storage and computational costs on vector search systems. Recent embedding compression methods, including Matryoshka-Adaptor (EMNLP 2024), Search-…

Dimensionality Reduction

Mix-of-Show: Decentralized Low-Rank Adaptation for Multi-Concept Customization of Diffusion Models

2023-05-29 · NeurIPS 2023 11 · YuChao Gu, Xintao Wang, Jay Zhangjie Wu, Yujun Shi 외

Public large-scale text-to-image diffusion models, such as Stable Diffusion, have gained significant attention from the community. These models can be easily customized for new concepts using low-rank adaptations (LoRAs)…

Attribute

I Want This Product but Different : Multimodal Retrieval with Synthetic Query Expansion

2021-02-17 · Ivona Tautkute, Tomasz Trzcinski

This paper addresses the problem of media retrieval using a multimodal query (a query which combines visual input with additional semantic information in natural language feedback). We propose a SynthTriplet GAN framewor…

multimodal generationRetrievalTriplet