paper-with-me

홈 › Papers

Augmentation-Adapted Retriever Improves Generalization of Language Models as Generic Plug-In

2023-05-27 · Zichun Yu, Chenyan Xiong, Shi Yu, Zhiyuan Liu

Retrieval augmentation can aid language models (LMs) in knowledge-intensive tasks by supplying them with external information. Prior works on retrieval augmentation usually jointly fine-tune the retriever and the LM, making them closely coupled. In this paper, we explore the scheme of generic retrieval plug-in: the retriever is to assist target LMs that may not be known beforehand or are unable to be fine-tuned together. To retrieve useful documents for unseen target LMs, we propose augmentation-adapted retriever (AAR), which learns LM's preferences obtained from a known source LM. Experiments on the MMLU and PopQA datasets demonstrate that our AAR trained with a small source LM is able to significantly improve the zero-shot generalization of larger target LMs ranging from 250M Flan-T5 to 175B InstructGPT. Further analysis indicates that the preferences of different LMs overlap, enabling AAR trained with a single source LM to serve as a generic plug-in for various target LMs. Our code is open-sourced at https://github.com/OpenMatch/Augmentation-Adapted-Retriever.

📄 PDF Abstract BibTeX arXiv:2305.17331

Code (2)

openmatch/augmentation-adapted-retriever 공식 구현 pytorch
ruc-nlpir/flashrag pytorch

Tasks

MMLURetrievalZero-shot Generalization

Methods 이 논문이 사용한 방법론

Flan-T5 Flan-T5 is the instruction fine-tuned version of T5 or Text-to-Text Transfer Transformer Language Model.

Similar Papers 제목 키워드 기반

Augmenting Zero-Shot Dense Retrievers with Plug-in Mixture-of-Memories

2023-02-07 · Suyu Ge, Chenyan Xiong, Corby Rosset, Arnold Overwijk 외

In this paper we improve the zero-shot generalization ability of language models via Mixture-Of-Memory Augmentation (MoMA), a mechanism that retrieves augmentation documents from multiple information corpora ("external m…

RetrievalZero-shot Generalization

DRAMA: Diverse Augmentation from Large Language Models to Smaller Dense Retrievers

2025-02-25 · Xueguang Ma, Xi Victoria Lin, Barlas Oguz, Jimmy Lin 외

Large language models (LLMs) have demonstrated strong effectiveness and robustness while fine-tuned as dense retrievers. However, their large parameter size brings significant inference time computational challenges, inc…

Contrastive Learning

ARMOR: Adaptive Retriever Optimization for Low-Resource Telecom Question Answering

2026-06-29 · Heshan Fernando, Quan Xiao, Yan Xin, Tianyi Chen arxiv

Telecom question answering (QA) is a challenging setting for retrieval-augmented generation (RAG): evidence is fragmented across standards, papers, encyclopedic resources, and web documents, and answers often hinge on te…

Semantic RetrievalQuestion AnsweringAnswer Generation

Differentiable Retrieval Augmentation via Generative Language Modeling for E-commerce Query Intent Classification

2023-08-18 · Chenyu Zhao, Yunjiang Jiang, Yiming Qiu, Han Zhang 외

Retrieval augmentation, which enhances downstream models by a knowledge retriever and an external corpus instead of by merely increasing the number of model parameters, has been successfully applied to many natural langu…

intent-classificationIntent ClassificationLanguage ModelingLanguage Modelling+4

CLAP: Coreference-Linked Augmentation for Passage Retrieval

2025-08-09 · Huanwei Xu, Lin Xu, Liang Yuan arxiv

Large Language Model (LLM)-based passage expansion has shown promise for enhancing first-stage retrieval, but often underperforms with dense retrievers due to semantic drift and misalignment with their pretrained semanti…

Passage Retrieval