paper-with-me

홈 › Papers

POQD: Performance-Oriented Query Decomposer for Multi-vector retrieval

2025-05-25 · Yaoyang Liu, Junlin Li, Yinjun Wu, Zhen Chen

Although Multi-Vector Retrieval (MVR) has achieved the state of the art on many information retrieval (IR) tasks, its performance highly depends on how to decompose queries into smaller pieces, say phrases or tokens. However, optimizing query decomposition for MVR performance is not end-to-end differentiable. Even worse, jointly solving this problem and training the downstream retrieval-based systems, say RAG systems could be highly inefficient. To overcome these challenges, we propose Performance-Oriented Query Decomposer (POQD), a novel query decomposition framework for MVR. POQD leverages one LLM for query decomposition and searches the optimal prompt with an LLM-based optimizer. We further propose an end-to-end training algorithm to alternatively optimize the prompt for query decomposition and the downstream models. This algorithm can achieve superior MVR performance at a reasonable training cost as our theoretical analysis suggests. POQD can be integrated seamlessly into arbitrary retrieval-based systems such as Retrieval-Augmented Generation (RAG) systems. Extensive empirical studies on representative RAG-based QA tasks show that POQD outperforms existing query decomposition strategies in both retrieval performance and end-to-end QA accuracy. POQD is available at https://github.com/PKU-SDS-lab/POQD-ICML25.

📄 PDF Abstract BibTeX arXiv:2505.19189

Code (1)

pku-sds-lab/poqd-icml25 공식 구현

Tasks

Information RetrievalRAGRetrievalRetrieval-augmented Generation

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
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 $x$…
WordPiece 설명 없음
Weight Decay 설명 없음
Multi-Head Attention 설명 없음

Similar Papers 제목 키워드 기반

OPERA: A Reinforcement Learning--Enhanced Orchestrated Planner-Executor Architecture for Reasoning-Oriented Multi-Hop Retrieval

2025-08-22 · Yu Liu, Yanbing Liu, Fangfang Yuan, Cong Cao 외 arxiv

Recent advances in large language models (LLMs) and dense retrievers have driven significant progress in retrieval-augmented generation (RAG). However, existing approaches face significant challenges in complex reasoning…

Reinforcement Learning

XDecomposer: Learning Prior-Free Set Decomposition for Multiphase X-ray Diffraction

2026-05-07 · Hanyu Gao, Bin Cao, Yunyue Su, Tong-Yi Zhang 외 arxiv

Multiphase powder X-ray diffraction (PXRD) analysis remains a fundamental bottleneck in structure identification, as real-world synthesis often produces complex mixtures whose constituent phases (components) cannot be re…

Planner-Centric Reinforcement Learning for Deep Research with Structure-Aware Reward

2026-05-29 · Mustafa Anis Hussain, Xinle Wu, Yao Lu arxiv

Deep research tasks require LLMs to plan what to investigate, retrieve evidence, and synthesize long-form answers across multiple branches of inquiry. Existing training paradigms either rely on short-form verifiable QA a…

Reinforcement Learning

DecomposeRL: Learning to Ask Useful, Informative, and Diverse Questions for Semi-Supervised, Traceable Claim Verification

2026-05-27 · Shubhashis Roy Dipta, Ankur Padia, Francis Ferraro arxiv

Claim verification splits between end-to-end classifiers that are accurate but yields no inspectable traces, and decomposition-based methods produce inspectable traces but lag performance on benchmark datasets. We propos…

Modality-Collaborative Low-Rank Decomposers for Few-Shot Video Domain Adaptation

2025-11-24 · Yuyang Wanyan, Xiaoshan Yang, Weiming Dong, Changsheng Xu arxiv

In this paper, we study the challenging task of Few-Shot Video Domain Adaptation (FSVDA). The multimodal nature of videos introduces unique challenges, necessitating the simultaneous consideration of both domain alignmen…

Domain Adaptation