@inproceedings{umar-etal-2025-enhancing,
title = "Enhancing Regulatory Compliance Through Automated Retrieval, Reranking, and Answer Generation",
author = {Umar, K{\"u}branur and
Do{\u{g}}an, Hakan and
{\"O}zcan, Onur and
Karakaya, {\.I}smail and
Karamanl{\i}o{\u{g}}lu, Alper and
Demirel, Berkan},
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-1.14/",
pages = "91--96",
abstract = "This paper explains a Retrieval-Augmented Generation (RAG) pipeline that optimizes reg- ularity compliance using a combination of em- bedding models (i.e. bge-m3, jina-embeddings- v3, e5-large-v2) with reranker (i.e. bge- reranker-v2-m3). To efficiently process long context passages, we introduce context aware chunking method. By using the RePASS met- ric, we ensure comprehensive coverage of obli- gations and minimizes contradictions, thereby setting a new benchmark for RAG-based regu- latory compliance systems. The experimen- tal results show that our best configuration achieves a score of 0.79 in Recall@10 and 0.66 in MAP@10 with LLaMA-3.1-8B model for answer generation."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="umar-etal-2025-enhancing">
<titleInfo>
<title>Enhancing Regulatory Compliance Through Automated Retrieval, Reranking, and Answer Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kübranur</namePart>
<namePart type="family">Umar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hakan</namePart>
<namePart type="family">Doğan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Onur</namePart>
<namePart type="family">Özcan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">İsmail</namePart>
<namePart type="family">Karakaya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alper</namePart>
<namePart type="family">Karamanlıoğlu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Berkan</namePart>
<namePart type="family">Demirel</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 paper explains a Retrieval-Augmented Generation (RAG) pipeline that optimizes reg- ularity compliance using a combination of em- bedding models (i.e. bge-m3, jina-embeddings- v3, e5-large-v2) with reranker (i.e. bge- reranker-v2-m3). To efficiently process long context passages, we introduce context aware chunking method. By using the RePASS met- ric, we ensure comprehensive coverage of obli- gations and minimizes contradictions, thereby setting a new benchmark for RAG-based regu- latory compliance systems. The experimen- tal results show that our best configuration achieves a score of 0.79 in Recall@10 and 0.66 in MAP@10 with LLaMA-3.1-8B model for answer generation.</abstract>
<identifier type="citekey">umar-etal-2025-enhancing</identifier>
<location>
<url>https://aclanthology.org/2025.regnlp-1.14/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>91</start>
<end>96</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Enhancing Regulatory Compliance Through Automated Retrieval, Reranking, and Answer Generation
%A Umar, Kübranur
%A Doğan, Hakan
%A Özcan, Onur
%A Karakaya, İsmail
%A Karamanlıoğlu, Alper
%A Demirel, Berkan
%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 umar-etal-2025-enhancing
%X This paper explains a Retrieval-Augmented Generation (RAG) pipeline that optimizes reg- ularity compliance using a combination of em- bedding models (i.e. bge-m3, jina-embeddings- v3, e5-large-v2) with reranker (i.e. bge- reranker-v2-m3). To efficiently process long context passages, we introduce context aware chunking method. By using the RePASS met- ric, we ensure comprehensive coverage of obli- gations and minimizes contradictions, thereby setting a new benchmark for RAG-based regu- latory compliance systems. The experimen- tal results show that our best configuration achieves a score of 0.79 in Recall@10 and 0.66 in MAP@10 with LLaMA-3.1-8B model for answer generation.
%U https://aclanthology.org/2025.regnlp-1.14/
%P 91-96
Markdown (Informal)
[Enhancing Regulatory Compliance Through Automated Retrieval, Reranking, and Answer Generation](https://aclanthology.org/2025.regnlp-1.14/) (Umar et al., RegNLP 2025)
ACL
- Kübranur Umar, Hakan Doğan, Onur Özcan, İsmail Karakaya, Alper Karamanlıoğlu, and Berkan Demirel. 2025. Enhancing Regulatory Compliance Through Automated Retrieval, Reranking, and Answer Generation. In Proceedings of the 1st Regulatory NLP Workshop (RegNLP 2025), pages 91–96, Abu Dhabi, UAE. Association for Computational Linguistics.