@inproceedings{paul-etal-2025-il,
title = "{IL}-{PCSR}: Legal Corpus for Prior Case and Statute Retrieval",
author = "Paul, Shounak and
Ghumare, Dhananjay and
Goyal, Pawan and
Ghosh, Saptarshi and
Modi, Ashutosh",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-main.738/",
doi = "10.18653/v1/2025.emnlp-main.738",
pages = "14588--14611",
ISBN = "979-8-89176-332-6",
abstract = "Identifying/retrieving relevant statutes and prior cases/precedents for a given legal situation are common tasks exercised by law practitioners. Researchers till date have addressed the two tasks independently, thus developing completely different datasets and models for each task; however, both retrieval tasks are inherently related, e.g., similar cases tend to cite similar statutes (due to similar factual situation). In this paper, we address this gap. We propose IL-PCSR (Indian Legal corpus for Prior Case and Statute Retrieval), which is a unique corpus that provides a common testbed for developing models for both the tasks (Statute Retrieval and Precedent Retrieval) that can exploit the dependence between the two. We experiment extensively with several baseline models on the tasks, including lexical models, semantic models and ensemble based on GNNs. Further, to exploit the dependence between the two tasks, we develop an LLM based re-ranking approach that gives the best performance."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="paul-etal-2025-il">
<titleInfo>
<title>IL-PCSR: Legal Corpus for Prior Case and Statute Retrieval</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shounak</namePart>
<namePart type="family">Paul</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dhananjay</namePart>
<namePart type="family">Ghumare</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pawan</namePart>
<namePart type="family">Goyal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saptarshi</namePart>
<namePart type="family">Ghosh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ashutosh</namePart>
<namePart type="family">Modi</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 2025 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-332-6</identifier>
</relatedItem>
<abstract>Identifying/retrieving relevant statutes and prior cases/precedents for a given legal situation are common tasks exercised by law practitioners. Researchers till date have addressed the two tasks independently, thus developing completely different datasets and models for each task; however, both retrieval tasks are inherently related, e.g., similar cases tend to cite similar statutes (due to similar factual situation). In this paper, we address this gap. We propose IL-PCSR (Indian Legal corpus for Prior Case and Statute Retrieval), which is a unique corpus that provides a common testbed for developing models for both the tasks (Statute Retrieval and Precedent Retrieval) that can exploit the dependence between the two. We experiment extensively with several baseline models on the tasks, including lexical models, semantic models and ensemble based on GNNs. Further, to exploit the dependence between the two tasks, we develop an LLM based re-ranking approach that gives the best performance.</abstract>
<identifier type="citekey">paul-etal-2025-il</identifier>
<identifier type="doi">10.18653/v1/2025.emnlp-main.738</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-main.738/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>14588</start>
<end>14611</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T IL-PCSR: Legal Corpus for Prior Case and Statute Retrieval
%A Paul, Shounak
%A Ghumare, Dhananjay
%A Goyal, Pawan
%A Ghosh, Saptarshi
%A Modi, Ashutosh
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-332-6
%F paul-etal-2025-il
%X Identifying/retrieving relevant statutes and prior cases/precedents for a given legal situation are common tasks exercised by law practitioners. Researchers till date have addressed the two tasks independently, thus developing completely different datasets and models for each task; however, both retrieval tasks are inherently related, e.g., similar cases tend to cite similar statutes (due to similar factual situation). In this paper, we address this gap. We propose IL-PCSR (Indian Legal corpus for Prior Case and Statute Retrieval), which is a unique corpus that provides a common testbed for developing models for both the tasks (Statute Retrieval and Precedent Retrieval) that can exploit the dependence between the two. We experiment extensively with several baseline models on the tasks, including lexical models, semantic models and ensemble based on GNNs. Further, to exploit the dependence between the two tasks, we develop an LLM based re-ranking approach that gives the best performance.
%R 10.18653/v1/2025.emnlp-main.738
%U https://aclanthology.org/2025.emnlp-main.738/
%U https://doi.org/10.18653/v1/2025.emnlp-main.738
%P 14588-14611
Markdown (Informal)
[IL-PCSR: Legal Corpus for Prior Case and Statute Retrieval](https://aclanthology.org/2025.emnlp-main.738/) (Paul et al., EMNLP 2025)
ACL
- Shounak Paul, Dhananjay Ghumare, Pawan Goyal, Saptarshi Ghosh, and Ashutosh Modi. 2025. IL-PCSR: Legal Corpus for Prior Case and Statute Retrieval. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 14588–14611, Suzhou, China. Association for Computational Linguistics.