@inproceedings{sun-etal-2025-two,
title = "A Two-Stage {LLM} System for Enhanced Regulatory Information Retrieval and Answer Generation",
author = "Sun, Fengzhao and
Yu, Jun and
Hou, Jiaming and
Lin, Yutong and
Liu, Tianyu",
editor = "Gokhan, Tuba and
Wang, Kexin and
Gurevych, Iryna and
Briscoe, Ted",
booktitle = "Proceedings of the 1st Regulatory NLP Workshop (RegNLP 2025)",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.regnlp-1.10/",
pages = "68--72",
abstract = "This technical report describes our methodology for the Regulatory Information Retrieval and Answer Generation (RIRAG) Shared Task, a component of the RegNLP workshop at COLING 2025. The challenge aims to effectively navigate and extract relevant information from regulatory texts to generate precise, coherent answers for compliance and obligation-related queries. To tackle subtask1, we introduce a two-stage approach comprising an initial output stage and a subsequent refinement stage. Initially, we fine-tune the LLaMa-2-7B model using LoRA to produce a preliminary output. This is followed by the application of an expert mechanism to enhance the results. For subtask2, we design specific prompt to facilitate the generation of high-quality answers. Consequently, our approach has achieved state-of-the-art performance on the leaderboard, which serves as a testament to the effectiveness and competitiveness of our proposed methodology."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sun-etal-2025-two">
<titleInfo>
<title>A Two-Stage LLM System for Enhanced Regulatory Information Retrieval and Answer Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fengzhao</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiaming</namePart>
<namePart type="family">Hou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yutong</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tianyu</namePart>
<namePart type="family">Liu</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 1st Regulatory NLP Workshop (RegNLP 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tuba</namePart>
<namePart type="family">Gokhan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kexin</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iryna</namePart>
<namePart type="family">Gurevych</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ted</namePart>
<namePart type="family">Briscoe</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 technical report describes our methodology for the Regulatory Information Retrieval and Answer Generation (RIRAG) Shared Task, a component of the RegNLP workshop at COLING 2025. The challenge aims to effectively navigate and extract relevant information from regulatory texts to generate precise, coherent answers for compliance and obligation-related queries. To tackle subtask1, we introduce a two-stage approach comprising an initial output stage and a subsequent refinement stage. Initially, we fine-tune the LLaMa-2-7B model using LoRA to produce a preliminary output. This is followed by the application of an expert mechanism to enhance the results. For subtask2, we design specific prompt to facilitate the generation of high-quality answers. Consequently, our approach has achieved state-of-the-art performance on the leaderboard, which serves as a testament to the effectiveness and competitiveness of our proposed methodology.</abstract>
<identifier type="citekey">sun-etal-2025-two</identifier>
<location>
<url>https://aclanthology.org/2025.regnlp-1.10/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>68</start>
<end>72</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Two-Stage LLM System for Enhanced Regulatory Information Retrieval and Answer Generation
%A Sun, Fengzhao
%A Yu, Jun
%A Hou, Jiaming
%A Lin, Yutong
%A Liu, Tianyu
%Y Gokhan, Tuba
%Y Wang, Kexin
%Y Gurevych, Iryna
%Y Briscoe, Ted
%S Proceedings of the 1st Regulatory NLP Workshop (RegNLP 2025)
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F sun-etal-2025-two
%X This technical report describes our methodology for the Regulatory Information Retrieval and Answer Generation (RIRAG) Shared Task, a component of the RegNLP workshop at COLING 2025. The challenge aims to effectively navigate and extract relevant information from regulatory texts to generate precise, coherent answers for compliance and obligation-related queries. To tackle subtask1, we introduce a two-stage approach comprising an initial output stage and a subsequent refinement stage. Initially, we fine-tune the LLaMa-2-7B model using LoRA to produce a preliminary output. This is followed by the application of an expert mechanism to enhance the results. For subtask2, we design specific prompt to facilitate the generation of high-quality answers. Consequently, our approach has achieved state-of-the-art performance on the leaderboard, which serves as a testament to the effectiveness and competitiveness of our proposed methodology.
%U https://aclanthology.org/2025.regnlp-1.10/
%P 68-72
Markdown (Informal)
[A Two-Stage LLM System for Enhanced Regulatory Information Retrieval and Answer Generation](https://aclanthology.org/2025.regnlp-1.10/) (Sun et al., RegNLP 2025)
ACL