<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kung-chang-2025-study">
    <titleInfo>
        <title>The Study of a Traffic Accident Information Collection Agent System Based on Fine-tuned Open-Source Large Language Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jo-Chi</namePart>
        <namePart type="family">Kung</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Chia-Hui</namePart>
        <namePart type="family">Chang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 37th Conference on Computational Linguistics and Speech Processing (ROCLING 2025)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Kai-Wei</namePart>
            <namePart type="family">Chang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ke-Han</namePart>
            <namePart type="family">Lu</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Chih-Kai</namePart>
            <namePart type="family">Yang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Zhi-Rui</namePart>
            <namePart type="family">Tam</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Wen-Yu</namePart>
            <namePart type="family">Chang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Chung-Che</namePart>
            <namePart type="family">Wang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">National Taiwan University, Taipei City, Taiwan</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-379-1</identifier>
    </relatedItem>
    <abstract>本研究提出了一套名為「交通事故資訊蒐集代理人」(Collision Care Guide, CCG)的系統架構,專注於事故初期階段的結構化資訊蒐集。CCG 整合三大模組:問題生成、資訊擷取及事故重建,透過多輪對話引導使用者敘述事故細節並轉換為結構化資料格式(TARF),同時生成可讀性敘述供核對。為滿足成本效益、隱私保護及部署彈性需求,本研究比較開源 Llama 模型(3B/8B 參數,完整微調及 4-bit PEFT 方法)與商業基準 GPT-4o-mini 的效能表現。結果顯示,資訊擷取模組欄位準確率高於 0.94,JSON 語義相似度達 0.995;問題生成模組語義相似度介於 0.85-0.88,問題表達更加精煉。微調模型在對話品質與資訊擷取的 LLM 評估中均獲得 4 分以上(滿分 5 分),與商業基準差距小於 0.5 分。研究證實開源模型經微調後能逼近商業模型效能,且量化版本在資源受限場景中具備高效能與部署潛力。CCG 的設計填補了事故初期互動式資訊蒐集的技術空白,為交通事故處理提供了高效且具成本優勢的解決方案。</abstract>
    <identifier type="citekey">kung-chang-2025-study</identifier>
    <location>
        <url>https://aclanthology.org/2025.rocling-main.8/</url>
    </location>
    <part>
        <date>2025-11</date>
        <extent unit="page">
            <start>71</start>
            <end>79</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T The Study of a Traffic Accident Information Collection Agent System Based on Fine-tuned Open-Source Large Language Models
%A Kung, Jo-Chi
%A Chang, Chia-Hui
%Y Chang, Kai-Wei
%Y Lu, Ke-Han
%Y Yang, Chih-Kai
%Y Tam, Zhi-Rui
%Y Chang, Wen-Yu
%Y Wang, Chung-Che
%S Proceedings of the 37th Conference on Computational Linguistics and Speech Processing (ROCLING 2025)
%D 2025
%8 November
%I Association for Computational Linguistics
%C National Taiwan University, Taipei City, Taiwan
%@ 979-8-89176-379-1
%F kung-chang-2025-study
%X 本研究提出了一套名為「交通事故資訊蒐集代理人」(Collision Care Guide, CCG)的系統架構,專注於事故初期階段的結構化資訊蒐集。CCG 整合三大模組:問題生成、資訊擷取及事故重建,透過多輪對話引導使用者敘述事故細節並轉換為結構化資料格式(TARF),同時生成可讀性敘述供核對。為滿足成本效益、隱私保護及部署彈性需求,本研究比較開源 Llama 模型(3B/8B 參數,完整微調及 4-bit PEFT 方法)與商業基準 GPT-4o-mini 的效能表現。結果顯示,資訊擷取模組欄位準確率高於 0.94,JSON 語義相似度達 0.995;問題生成模組語義相似度介於 0.85-0.88,問題表達更加精煉。微調模型在對話品質與資訊擷取的 LLM 評估中均獲得 4 分以上(滿分 5 分),與商業基準差距小於 0.5 分。研究證實開源模型經微調後能逼近商業模型效能,且量化版本在資源受限場景中具備高效能與部署潛力。CCG 的設計填補了事故初期互動式資訊蒐集的技術空白,為交通事故處理提供了高效且具成本優勢的解決方案。
%U https://aclanthology.org/2025.rocling-main.8/
%P 71-79

Markdown (Informal)

[The Study of a Traffic Accident Information Collection Agent System Based on Fine-tuned Open-Source Large Language Models](https://aclanthology.org/2025.rocling-main.8/) (Kung & Chang, ROCLING 2025)

• The Study of a Traffic Accident Information Collection Agent System Based on Fine-tuned Open-Source Large Language Models (Kung & Chang, ROCLING 2025)

ACL

• Jo-Chi Kung and Chia-Hui Chang. 2025. The Study of a Traffic Accident Information Collection Agent System Based on Fine-tuned Open-Source Large Language Models. In Proceedings of the 37th Conference on Computational Linguistics and Speech Processing (ROCLING 2025), pages 71–79, National Taiwan University, Taipei City, Taiwan. Association for Computational Linguistics.