<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="louis-etal-2025-pisco">
    <titleInfo>
        <title>PISCO: Pretty Simple Compression for Retrieval-Augmented Generation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Maxime</namePart>
        <namePart type="family">Louis</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hervé</namePart>
        <namePart type="family">Déjean</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Stéphane</namePart>
        <namePart type="family">Clinchant</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: ACL 2025</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Wanxiang</namePart>
            <namePart type="family">Che</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Joyce</namePart>
            <namePart type="family">Nabende</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ekaterina</namePart>
            <namePart type="family">Shutova</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mohammad</namePart>
            <namePart type="given">Taher</namePart>
            <namePart type="family">Pilehvar</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Vienna, Austria</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-256-5</identifier>
    </relatedItem>
    <abstract>Retrieval-Augmented Generation (RAG) pipelines enhance Large Language Models (LLMs) by retrieving relevant documents, but they face scalability issues due to high inference costs and limited context size. Document compression is a practical solution, but current soft compression methods often suffer from accuracy losses and require extensive pretraining. In this paper, we introduce PISCO, a novel method that achieves a 16x compression rate with minimal accuracy loss (0-3%) across diverse RAG-based question-answering (QA) tasks. Unlike existing approaches, PISCO requires no pretraining or annotated data, relying solely on sequence-level knowledge distillation from document-based questions. With the ability to fine-tune a 7-10B LLM in 24 hours on a single A100 GPU, PISCO offers a highly efficient and scalable solution. We present comprehensive experiments showing that PISCO outperforms existing compression models by 8% in accuracy.</abstract>
    <identifier type="citekey">louis-etal-2025-pisco</identifier>
    <identifier type="doi">10.18653/v1/2025.findings-acl.800</identifier>
    <location>
        <url>https://aclanthology.org/2025.findings-acl.800/</url>
    </location>
    <part>
        <date>2025-07</date>
        <extent unit="page">
            <start>15506</start>
            <end>15521</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T PISCO: Pretty Simple Compression for Retrieval-Augmented Generation
%A Louis, Maxime
%A Déjean, Hervé
%A Clinchant, Stéphane
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Findings of the Association for Computational Linguistics: ACL 2025
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-256-5
%F louis-etal-2025-pisco
%X Retrieval-Augmented Generation (RAG) pipelines enhance Large Language Models (LLMs) by retrieving relevant documents, but they face scalability issues due to high inference costs and limited context size. Document compression is a practical solution, but current soft compression methods often suffer from accuracy losses and require extensive pretraining. In this paper, we introduce PISCO, a novel method that achieves a 16x compression rate with minimal accuracy loss (0-3%) across diverse RAG-based question-answering (QA) tasks. Unlike existing approaches, PISCO requires no pretraining or annotated data, relying solely on sequence-level knowledge distillation from document-based questions. With the ability to fine-tune a 7-10B LLM in 24 hours on a single A100 GPU, PISCO offers a highly efficient and scalable solution. We present comprehensive experiments showing that PISCO outperforms existing compression models by 8% in accuracy.
%R 10.18653/v1/2025.findings-acl.800
%U https://aclanthology.org/2025.findings-acl.800/
%U https://doi.org/10.18653/v1/2025.findings-acl.800
%P 15506-15521

Markdown (Informal)

[PISCO: Pretty Simple Compression for Retrieval-Augmented Generation](https://aclanthology.org/2025.findings-acl.800/) (Louis et al., Findings 2025)

• PISCO: Pretty Simple Compression for Retrieval-Augmented Generation (Louis et al., Findings 2025)

ACL

• Maxime Louis, Hervé Déjean, and Stéphane Clinchant. 2025. PISCO: Pretty Simple Compression for Retrieval-Augmented Generation. In Findings of the Association for Computational Linguistics: ACL 2025, pages 15506–15521, Vienna, Austria. Association for Computational Linguistics.