Legal text summarization via judicial syllogism with large language models

Abstract Legal judgment documents are typically lengthy, complex, and filled with domain-specific language. Existing summarization methods often struggle to capture the essential legal reasoning, frequently omitting critical details such as the applicable law and the logical connection between facts...

Full description

Saved in:
Bibliographic Details
Main Authors: Yumei Song, Yongbin Qin, Ruizhang Huang, Yanping Chen, Chuan Lin
Format: Article
Language:English
Published: Springer 2025-07-01
Series:Journal of King Saud University: Computer and Information Sciences
Subjects:
Online Access:https://doi.org/10.1007/s44443-025-00113-3
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849235647788744704
author Yumei Song
Yongbin Qin
Ruizhang Huang
Yanping Chen
Chuan Lin
author_facet Yumei Song
Yongbin Qin
Ruizhang Huang
Yanping Chen
Chuan Lin
author_sort Yumei Song
collection DOAJ
description Abstract Legal judgment documents are typically lengthy, complex, and filled with domain-specific language. Existing summarization methods often struggle to capture the essential legal reasoning, frequently omitting critical details such as the applicable law and the logical connection between facts and outcomes-resulting in summaries that lack interpretability and coherence. Recent advances in large language models (LLMs) have shown strong capabilities in multi-step reasoning and language generation, making them a promising foundation for tackling the challenges of legal summarization. However, their potential remains underutilized in the legal domain due to the need for explicit legal logic and structured inference. To address this issue, we propose a novel summarization framework based on judicial syllogism using large language models (LLMs). Specifically, we leverage the large language model guiding it explicitly to emulate classical judicial reasoning: extracting the major premise (applicable legal provisions), the minor premise (case-specific facts), and finally deducing the conclusion (judgment outcome). This structured reasoning is operationalized through carefully designed prompt engineering and fine-tuning techniques, enabling the model to reason step-by-step like a human judge. We evaluate our proposed method on two judicial summarization datasets. Experimental results demonstrate that our judicial syllogism approach achieves competitive performance compared to several strong baseline LLMs. Ablation studies further verify that each component (law, facts, conclusion) of the judicial syllogism contributes meaningfully to the summarization quality. Our findings clearly indicate that embedding explicit judicial syllogistic reasoning significantly enhances the accuracy and logical coherence of legal text summarization.
format Article
id doaj-art-d10c20ffbc694126a131311644f43c8a
institution Kabale University
issn 1319-1578
2213-1248
language English
publishDate 2025-07-01
publisher Springer
record_format Article
series Journal of King Saud University: Computer and Information Sciences
spelling doaj-art-d10c20ffbc694126a131311644f43c8a2025-08-20T04:02:42ZengSpringerJournal of King Saud University: Computer and Information Sciences1319-15782213-12482025-07-0137511310.1007/s44443-025-00113-3Legal text summarization via judicial syllogism with large language modelsYumei Song0Yongbin Qin1Ruizhang Huang2Yanping Chen3Chuan Lin4Engineering Research Center of Text Computing & Cognitive Intelligence Ministry of Education, Guizhou UniversityEngineering Research Center of Text Computing & Cognitive Intelligence Ministry of Education, Guizhou UniversityEngineering Research Center of Text Computing & Cognitive Intelligence Ministry of Education, Guizhou UniversityEngineering Research Center of Text Computing & Cognitive Intelligence Ministry of Education, Guizhou UniversityEngineering Research Center of Text Computing & Cognitive Intelligence Ministry of Education, Guizhou UniversityAbstract Legal judgment documents are typically lengthy, complex, and filled with domain-specific language. Existing summarization methods often struggle to capture the essential legal reasoning, frequently omitting critical details such as the applicable law and the logical connection between facts and outcomes-resulting in summaries that lack interpretability and coherence. Recent advances in large language models (LLMs) have shown strong capabilities in multi-step reasoning and language generation, making them a promising foundation for tackling the challenges of legal summarization. However, their potential remains underutilized in the legal domain due to the need for explicit legal logic and structured inference. To address this issue, we propose a novel summarization framework based on judicial syllogism using large language models (LLMs). Specifically, we leverage the large language model guiding it explicitly to emulate classical judicial reasoning: extracting the major premise (applicable legal provisions), the minor premise (case-specific facts), and finally deducing the conclusion (judgment outcome). This structured reasoning is operationalized through carefully designed prompt engineering and fine-tuning techniques, enabling the model to reason step-by-step like a human judge. We evaluate our proposed method on two judicial summarization datasets. Experimental results demonstrate that our judicial syllogism approach achieves competitive performance compared to several strong baseline LLMs. Ablation studies further verify that each component (law, facts, conclusion) of the judicial syllogism contributes meaningfully to the summarization quality. Our findings clearly indicate that embedding explicit judicial syllogistic reasoning significantly enhances the accuracy and logical coherence of legal text summarization.https://doi.org/10.1007/s44443-025-00113-3Natural language processingNatural language generationLegal text summarizationJudicial syllogismPrompt engineering
spellingShingle Yumei Song
Yongbin Qin
Ruizhang Huang
Yanping Chen
Chuan Lin
Legal text summarization via judicial syllogism with large language models
Journal of King Saud University: Computer and Information Sciences
Natural language processing
Natural language generation
Legal text summarization
Judicial syllogism
Prompt engineering
title Legal text summarization via judicial syllogism with large language models
title_full Legal text summarization via judicial syllogism with large language models
title_fullStr Legal text summarization via judicial syllogism with large language models
title_full_unstemmed Legal text summarization via judicial syllogism with large language models
title_short Legal text summarization via judicial syllogism with large language models
title_sort legal text summarization via judicial syllogism with large language models
topic Natural language processing
Natural language generation
Legal text summarization
Judicial syllogism
Prompt engineering
url https://doi.org/10.1007/s44443-025-00113-3
work_keys_str_mv AT yumeisong legaltextsummarizationviajudicialsyllogismwithlargelanguagemodels
AT yongbinqin legaltextsummarizationviajudicialsyllogismwithlargelanguagemodels
AT ruizhanghuang legaltextsummarizationviajudicialsyllogismwithlargelanguagemodels
AT yanpingchen legaltextsummarizationviajudicialsyllogismwithlargelanguagemodels
AT chuanlin legaltextsummarizationviajudicialsyllogismwithlargelanguagemodels