@inproceedings{saha-etal-2026-inlegallaysum,
title = "{I}n{L}egal{L}ay{S}um: A Novel Benchmark for Lay Summarization of {I}ndian Legal Documents",
author = "Saha, Trishita and
Datta, Debtanu and
Tiwari, Shubham and
Kaushal, Mohit and
Rathore, Priyank and
Pandit, Mohammad Khalid and
Goyal, Pawan and
Ghosh, Saptarshi",
editor = "Zhang, Yue and
Xu, Ruifeng and
Purwarianti, Ayu and
Rong, Tong and
Suzuki, Jun",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {IJCNLP}-{AACL} 2026",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-aacl.156/",
pages = "3099--3123",
ISBN = "979-8-89176-444-6",
abstract = "Legal documents are often lengthy and contain domain-specific terminology and complex legal reasoning, making them difficult for the general public to understand. This challenge is further amplified in the Indian context, where a large portion of the population lacks proficiency in complex English. Although automatic legal summarization has been studied, most existing approaches generate summaries intended for legal professionals and thus remain difficult for laypeople. To address this gap, we introduce InLegalLaySum, the first benchmark for lay summarization of Indian legal documents. InLegalLaySum comprises 9,570 judgements from the Supreme Court and several High Courts of India paired with expert-written summaries in English. We benchmark a wide range of generative models (ranging from 160M to 7B parameters) and perform comprehensive experiments with multiple training strategies, including supervised fine-tuning (SFT) and direct preference optimization (DPO). We observed that the hybrid SFT+DPO training achieved superior performance across readability metrics, which is further validated by domain experts."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="saha-etal-2026-inlegallaysum">
<titleInfo>
<title>InLegalLaySum: A Novel Benchmark for Lay Summarization of Indian Legal Documents</title>
</titleInfo>
<name type="personal">
<namePart type="given">Trishita</namePart>
<namePart type="family">Saha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Debtanu</namePart>
<namePart type="family">Datta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shubham</namePart>
<namePart type="family">Tiwari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Kaushal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Priyank</namePart>
<namePart type="family">Rathore</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Khalid</namePart>
<namePart type="family">Pandit</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>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruifeng</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayu</namePart>
<namePart type="family">Purwarianti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Rong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Suzuki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-444-6</identifier>
</relatedItem>
<abstract>Legal documents are often lengthy and contain domain-specific terminology and complex legal reasoning, making them difficult for the general public to understand. This challenge is further amplified in the Indian context, where a large portion of the population lacks proficiency in complex English. Although automatic legal summarization has been studied, most existing approaches generate summaries intended for legal professionals and thus remain difficult for laypeople. To address this gap, we introduce InLegalLaySum, the first benchmark for lay summarization of Indian legal documents. InLegalLaySum comprises 9,570 judgements from the Supreme Court and several High Courts of India paired with expert-written summaries in English. We benchmark a wide range of generative models (ranging from 160M to 7B parameters) and perform comprehensive experiments with multiple training strategies, including supervised fine-tuning (SFT) and direct preference optimization (DPO). We observed that the hybrid SFT+DPO training achieved superior performance across readability metrics, which is further validated by domain experts.</abstract>
<identifier type="citekey">saha-etal-2026-inlegallaysum</identifier>
<location>
<url>https://aclanthology.org/2026.findings-aacl.156/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>3099</start>
<end>3123</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T InLegalLaySum: A Novel Benchmark for Lay Summarization of Indian Legal Documents
%A Saha, Trishita
%A Datta, Debtanu
%A Tiwari, Shubham
%A Kaushal, Mohit
%A Rathore, Priyank
%A Pandit, Mohammad Khalid
%A Goyal, Pawan
%A Ghosh, Saptarshi
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-444-6
%F saha-etal-2026-inlegallaysum
%X Legal documents are often lengthy and contain domain-specific terminology and complex legal reasoning, making them difficult for the general public to understand. This challenge is further amplified in the Indian context, where a large portion of the population lacks proficiency in complex English. Although automatic legal summarization has been studied, most existing approaches generate summaries intended for legal professionals and thus remain difficult for laypeople. To address this gap, we introduce InLegalLaySum, the first benchmark for lay summarization of Indian legal documents. InLegalLaySum comprises 9,570 judgements from the Supreme Court and several High Courts of India paired with expert-written summaries in English. We benchmark a wide range of generative models (ranging from 160M to 7B parameters) and perform comprehensive experiments with multiple training strategies, including supervised fine-tuning (SFT) and direct preference optimization (DPO). We observed that the hybrid SFT+DPO training achieved superior performance across readability metrics, which is further validated by domain experts.
%U https://aclanthology.org/2026.findings-aacl.156/
%P 3099-3123
Markdown (Informal)
[InLegalLaySum: A Novel Benchmark for Lay Summarization of Indian Legal Documents](https://aclanthology.org/2026.findings-aacl.156/) (Saha et al., Findings 2026)
ACL
- Trishita Saha, Debtanu Datta, Shubham Tiwari, Mohit Kaushal, Priyank Rathore, Mohammad Khalid Pandit, Pawan Goyal, and Saptarshi Ghosh. 2026. InLegalLaySum: A Novel Benchmark for Lay Summarization of Indian Legal Documents. In Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026, pages 3099–3123, Hengqin, China. Association for Computational Linguistics.