paper-with-me

Papers

Soft Prompt Decoding for Multilingual Dense Retrieval

2023-05-15 · Zhiqi Huang, Hansi Zeng, Hamed Zamani, James Allan

In this work, we explore a Multilingual Information Retrieval (MLIR) task, where the collection includes documents in multiple languages. We demonstrate that applying state-of-the-art approaches developed for cross-lingual information retrieval to MLIR tasks leads to sub-optimal performance. This is due to the heterogeneous and imbalanced nature of multilingual collections -- some languages are better represented in the collection and some benefit from large-scale training data. To address this issue, we present KD-SPD, a novel soft prompt decoding approach for MLIR that implicitly "translates" the representation of documents in different languages into the same embedding space. To address the challenges of data scarcity and imbalance, we introduce a knowledge distillation strategy. The teacher model is trained on rich English retrieval data, and by leveraging bi-text data, our distillation framework transfers its retrieval knowledge to the multilingual document encoder. Therefore, our approach does not require any multilingual retrieval training data. Extensive experiments on three MLIR datasets with a total of 15 languages demonstrate that KD-SPD significantly outperforms competitive baselines in all cases. We conduct extensive analyses to show that our method has less language bias and better zero-shot transfer ability towards new languages.

📄 PDF Abstract BibTeX arXiv:2305.09025

Code (0)

등록된 구현이 없습니다.

Tasks

Cross-Lingual Information RetrievalInformation RetrievalKnowledge DistillationRetrieval

Methods 이 논문이 사용한 방법론

Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…

Similar Papers 제목 키워드 기반

Leveraging LLMs for Synthesizing Training Data Across Many Languages in Multilingual Dense Retrieval

2023-11-10 · Nandan Thakur, Jianmo Ni, Gustavo Hernández Ábrego, John Wieting 외

There has been limited success for dense retrieval models in multilingual retrieval, due to uneven and scarce training data available across multiple languages. Synthetic training data generation is promising (e.g., InPa…

Language ModelingLanguage ModellingLarge Language ModelRetrieval

Soft Prompt Tuning for Augmenting Dense Retrieval with Large Language Models

2023-07-17 · Zhiyuan Peng, Xuyang Wu, Qifan Wang, Yi Fang

Dense retrieval (DR) converts queries and documents into dense embeddings and measures the similarity between queries and documents in vector space. One of the challenges in DR is the lack of domain-specific training dat…

RetrievalTAGTransfer Learning

Language Drift in Multilingual Retrieval-Augmented Generation: Characterization and Decoding-Time Mitigation

2025-11-13 · Bo Li, Zhenghua Xu, Rui Xie arxiv

Multilingual Retrieval-Augmented Generation (RAG) enables large language models (LLMs) to perform knowledge-intensive tasks in multilingual settings by leveraging retrieved documents as external evidence. However, when t…

Non-negative Elastic Net Decoding for Information Retrieval

2026-06-16 · Koki Okajima, Yasutoshi Ida, Tsukasa Yoshida, Yasuaki Nakamura arxiv

Dense retrieval has become the dominant paradigm in information retrieval, in which each document is scored against a query by the inner product of their vector embeddings, and the top-$k$ documents by score are retrieve…

Information Retrieval

Unsupervised Multilingual Dense Retrieval via Generative Pseudo Labeling

2024-03-06 · Chao-Wei Huang, Chen-An Li, Tsu-Yuan Hsu, Chen-Yu Hsu 외

Dense retrieval methods have demonstrated promising performance in multilingual information retrieval, where queries and documents can be in different languages. However, dense retrievers typically require a substantial …

Information RetrievalRetrieval