<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="skipanes-etal-2025-enhancing">
    <titleInfo>
        <title>Enhancing Criminal Investigation Analysis with Summarization and Memory-based Retrieval-Augmented Generation: A Comprehensive Evaluation of Real Case Data</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Mads</namePart>
        <namePart type="family">Skipanes</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">rgensen,</namePart>
        <namePart type="given">Tollef</namePart>
        <namePart type="given">Emil</namePart>
        <namePart type="family">JÃ</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kyle</namePart>
        <namePart type="family">Porter</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Gianluca</namePart>
        <namePart type="family">Demartini</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sule</namePart>
        <namePart type="given">Yildirim</namePart>
        <namePart type="family">Yayilgan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-01</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 31st International Conference on Computational Linguistics</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Owen</namePart>
            <namePart type="family">Rambow</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Leo</namePart>
            <namePart type="family">Wanner</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Marianna</namePart>
            <namePart type="family">Apidianaki</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Hend</namePart>
            <namePart type="family">Al-Khalifa</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Barbara</namePart>
            <namePart type="given">Di</namePart>
            <namePart type="family">Eugenio</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Steven</namePart>
            <namePart type="family">Schockaert</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Abu Dhabi, UAE</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>This study introduces KriRAG, a novel Retrieval-Augmented Generation (RAG) architecture designed to assist criminal investigators in analyzing information and overcoming the challenge of information overload. KriRAG structures and summarizes extensive document collections based on existing investigative queries, providing relevant document references and detailed answers for each query. Working with unstructured data from two homicide case files comprising approximately 3,700 documents and 13,000 pages, a comprehensive evaluation methodology is established, incorporating semantic retrieval, scoring, reasoning, and query response accuracy. The system‘s outputs are evaluated against queries and answers provided by criminal investigators, demonstrating promising performance with 97.5% accuracy in relevance assessment and 77.5% accuracy for query responses. These findings provide a rigorous foundation for other query-oriented and open-ended retrieval applications. KriRAG is designed to run offline on limited hardware, ensuring sensitive data handling and on-device availability.</abstract>
    <identifier type="citekey">skipanes-etal-2025-enhancing</identifier>
    <location>
        <url>https://aclanthology.org/2025.coling-main.334/</url>
    </location>
    <part>
        <date>2025-01</date>
        <extent unit="page">
            <start>4993</start>
            <end>5010</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Enhancing Criminal Investigation Analysis with Summarization and Memory-based Retrieval-Augmented Generation: A Comprehensive Evaluation of Real Case Data
%A Skipanes, Mads
%A JÃ, rgensen, Tollef Emil
%A Porter, Kyle
%A Demartini, Gianluca
%A Yayilgan, Sule Yildirim
%Y Rambow, Owen
%Y Wanner, Leo
%Y Apidianaki, Marianna
%Y Al-Khalifa, Hend
%Y Eugenio, Barbara Di
%Y Schockaert, Steven
%S Proceedings of the 31st International Conference on Computational Linguistics
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F skipanes-etal-2025-enhancing
%X This study introduces KriRAG, a novel Retrieval-Augmented Generation (RAG) architecture designed to assist criminal investigators in analyzing information and overcoming the challenge of information overload. KriRAG structures and summarizes extensive document collections based on existing investigative queries, providing relevant document references and detailed answers for each query. Working with unstructured data from two homicide case files comprising approximately 3,700 documents and 13,000 pages, a comprehensive evaluation methodology is established, incorporating semantic retrieval, scoring, reasoning, and query response accuracy. The system‘s outputs are evaluated against queries and answers provided by criminal investigators, demonstrating promising performance with 97.5% accuracy in relevance assessment and 77.5% accuracy for query responses. These findings provide a rigorous foundation for other query-oriented and open-ended retrieval applications. KriRAG is designed to run offline on limited hardware, ensuring sensitive data handling and on-device availability.
%U https://aclanthology.org/2025.coling-main.334/
%P 4993-5010

Markdown (Informal)

[Enhancing Criminal Investigation Analysis with Summarization and Memory-based Retrieval-Augmented Generation: A Comprehensive Evaluation of Real Case Data](https://aclanthology.org/2025.coling-main.334/) (Skipanes et al., COLING 2025)

• Enhancing Criminal Investigation Analysis with Summarization and Memory-based Retrieval-Augmented Generation: A Comprehensive Evaluation of Real Case Data (Skipanes et al., COLING 2025)

ACL

• Mads Skipanes, Tollef Emil JÃ, rgensen, Kyle Porter, Gianluca Demartini, and Sule Yildirim Yayilgan. 2025. Enhancing Criminal Investigation Analysis with Summarization and Memory-based Retrieval-Augmented Generation: A Comprehensive Evaluation of Real Case Data. In Proceedings of the 31st International Conference on Computational Linguistics, pages 4993–5010, Abu Dhabi, UAE. Association for Computational Linguistics.