Optimizing Multi-Stage Language Models for Effective Text Retrieval
Efficient text retrieval is critical for applications such as legal document analysis, particularly in specialized contexts like Japanese legal systems. Existing retrieval methods often underperform in such domain-specific scenarios, necessitating tailored approaches. In this paper, we introduce a novel two-phase text retrieval pipeline optimized for Japanese legal datasets. Our method leverages advanced language models to achieve state-of-the-art performance, significantly improving retrieval efficiency and accuracy. To further enhance robustness and adaptability, we incorporate an ensemble model that integrates multiple retrieval strategies, resulting in superior outcomes across diverse tasks. Extensive experiments validate the effectiveness of our approach, demonstrating strong performance on both Japanese legal datasets and widely recognized benchmarks like MS-MARCO. Our work establishes new standards for text retrieval in domain-specific and general contexts, providing a comprehensive solution for addressing complex queries in legal and multilingual environments.
Code (0)
등록된 구현이 없습니다.
Tasks
RetrievalText RetrievalSimilar Papers 제목 키워드 기반
HLATR: Enhance Multi-stage Text Retrieval with Hybrid List Aware Transformer Reranking
Deep pre-trained language models (e,g. BERT) are effective at large-scale text retrieval task. Existing text retrieval systems with state-of-the-art performance usually adopt a retrieve-then-reranking architecture due to…
Passage RankingPassage Re-RankingRerankingRetrieval+1Optimizing Instructions and Demonstrations for Multi-Stage Language Model Programs
Language Model Programs, i.e. sophisticated pipelines of modular language model (LM) calls, are increasingly advancing NLP tasks, but they require crafting prompts that are jointly effective for all modules. We study pro…
Language ModelingLanguage ModellingNavigateOptimizing Low-Resource Language Model Training: Comprehensive Analysis of Multi-Epoch, Multi-Lingual, and Two-Stage Approaches
In this paper, we address the challenge of optimizing training setups for Large Language Models (LLMs) of low-resource language with a limited amount of corpus. Existing works adopt multi-epoch, multi-lingual, and two-st…
Language ModelingLanguage ModellingMOSAIC: Masked Objective with Selective Adaptation for In-domain Contrastive Learning
We introduce MOSAIC (Masked Objective with Selective Adaptation for In-domain Contrastive learning), a multi-stage framework for domain adaptation of text embedding models that incorporates joint domain-specific masked s…
Contrastive LearningDomain AdaptationMetaDreamer: Efficient Text-to-3D Creation With Disentangling Geometry and Texture
Generative models for 3D object synthesis have seen significant advancements with the incorporation of prior knowledge distilled from 2D diffusion models. Nevertheless, challenges persist in the form of multi-view geomet…
3D GenerationText to 3D