LMAR: Language Model Augmented Retriever for Domain-specific Knowledge Indexing

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhao, Yao, Ding, Yantian, Zhang, Zhiyue, Yao, Dapeng, Xu, Yanxun
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915492215652352
author Zhao, Yao
Ding, Yantian
Zhang, Zhiyue
Yao, Dapeng
Xu, Yanxun
author_facet Zhao, Yao
Ding, Yantian
Zhang, Zhiyue
Yao, Dapeng
Xu, Yanxun
contents Retrieval Augmented Generation (RAG) systems often struggle with domain-specific knowledge due to performance deterioration of pre-trained embeddings and prohibitive computational costs of large language model (LLM)-based retrievers. While fine-tuning data augmentation embedding models offers a promising direction, its effectiveness is limited by the need for high-quality training data and reliable chunking strategies that preserve contextual integrity. We propose LMAR (Language Model Augmented Retriever), a model-agnostic framework that addresses these challenges by combining LLM-guided data synthesis with contrastive embedding adaptation and efficient text clustering. LMAR consists of a two-stage pipeline: (1) Triplet sampling and synthetic data augmentation, where LLMs act as both labeler and validator to ensure high-fidelity supervision throughout the pipeline. Experimental results across multiple domain-specific benchmark datasets demonstrate that LMAR outperforms multiple baseline models, while maintaining moderate hardware requirements and low latency. Its model-agnostic nature further enables seamless integration with emerging RAG architectures and text embedding models, ensuring continual improvements without redesigning the pipeline. These results highlight LMAR as a practical and cost-effective solution for scalable domain-specific adaptation.
format Preprint
id arxiv_https___arxiv_org_abs_2508_05672
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LMAR: Language Model Augmented Retriever for Domain-specific Knowledge Indexing
Zhao, Yao
Ding, Yantian
Zhang, Zhiyue
Yao, Dapeng
Xu, Yanxun
Information Retrieval
Artificial Intelligence
Retrieval Augmented Generation (RAG) systems often struggle with domain-specific knowledge due to performance deterioration of pre-trained embeddings and prohibitive computational costs of large language model (LLM)-based retrievers. While fine-tuning data augmentation embedding models offers a promising direction, its effectiveness is limited by the need for high-quality training data and reliable chunking strategies that preserve contextual integrity. We propose LMAR (Language Model Augmented Retriever), a model-agnostic framework that addresses these challenges by combining LLM-guided data synthesis with contrastive embedding adaptation and efficient text clustering. LMAR consists of a two-stage pipeline: (1) Triplet sampling and synthetic data augmentation, where LLMs act as both labeler and validator to ensure high-fidelity supervision throughout the pipeline. Experimental results across multiple domain-specific benchmark datasets demonstrate that LMAR outperforms multiple baseline models, while maintaining moderate hardware requirements and low latency. Its model-agnostic nature further enables seamless integration with emerging RAG architectures and text embedding models, ensuring continual improvements without redesigning the pipeline. These results highlight LMAR as a practical and cost-effective solution for scalable domain-specific adaptation.
title LMAR: Language Model Augmented Retriever for Domain-specific Knowledge Indexing
topic Information Retrieval
Artificial Intelligence
url https://arxiv.org/abs/2508.05672