A Demonstration of a Semi-Structured Legal Reasoning Framework

Hannes Westermann

doi:10.1145/3769126.3769196

A Demonstration of a Semi-Structured Legal Reasoning Framework

Hannes Westermann^*

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceeding › Academic › peer-review

Abstract

Legal reasoning strikes a balance between structured elements (i.e. legal criteria and their connections) and unstructured elements (i.e. about of the applicability of open-textured legal terms). Expert systems perform well on the former task, while large language models offer significant potential in the latter style of reasoning. In this demonstration, we present the DALLMA framework, which enables the combination of these two approaches, for semi-structured reasoning. This approach has the potential to assist in many legal reasoning and drafting tasks, while reducing the risks of hallucinations, with important implications for e.g. access to justice.

Original language	English
Title of host publication	Proceedings of the Twentieth International Conference on Artificial Intelligence and Law
Editors	Juliano Maranhao
Place of Publication	New York
Publisher	Association for Computing Machinery (ACM)
Pages	504-505
Number of pages	2
ISBN (Electronic)	9798400719394
DOIs	https://doi.org/10.1145/3769126.3769196
Publication status	Published - 13 Jan 2026
Event	20th International Conference on Artificial Intelligence and Law, ICAIL 2025 - Chicago, United States Duration: 16 Jun 2025 → 20 Jun 2025 https://sites.northwestern.edu/icail2025/

Conference

Conference	20th International Conference on Artificial Intelligence and Law, ICAIL 2025
Abbreviated title	ICAIL 2025
Country/Territory	United States
City	Chicago
Period	16/06/25 → 20/06/25
Internet address	https://sites.northwestern.edu/icail2025/

Keywords

access to justice
forms
Generative AI
Large Language Models
legal reasoning

Access to Document

10.1145/3769126.3769196Licence: CC BY

Cite this

@inproceedings{29b6bfdcf2b746baa5cf8be62b9c6229,

title = "A Demonstration of a Semi-Structured Legal Reasoning Framework",

abstract = "Legal reasoning strikes a balance between structured elements (i.e. legal criteria and their connections) and unstructured elements (i.e. about of the applicability of open-textured legal terms). Expert systems perform well on the former task, while large language models offer significant potential in the latter style of reasoning. In this demonstration, we present the DALLMA framework, which enables the combination of these two approaches, for semi-structured reasoning. This approach has the potential to assist in many legal reasoning and drafting tasks, while reducing the risks of hallucinations, with important implications for e.g. access to justice.",

keywords = "access to justice, forms, Generative AI, Large Language Models, legal reasoning",

author = "Hannes Westermann",

note = "Publisher Copyright: {\textcopyright} 2025 Copyright held by the owner/author(s).; 20th International Conference on Artificial Intelligence and Law, ICAIL 2025, ICAIL 2025 ; Conference date: 16-06-2025 Through 20-06-2025",

year = "2026",

month = jan,

day = "13",

doi = "10.1145/3769126.3769196",

language = "English",

pages = "504--505",

editor = "Juliano Maranhao",

booktitle = "Proceedings of the Twentieth International Conference on Artificial Intelligence and Law",

publisher = "Association for Computing Machinery (ACM)",

address = "United States",

url = "https://sites.northwestern.edu/icail2025/",

}

Westermann, H 2026, A Demonstration of a Semi-Structured Legal Reasoning Framework. in J Maranhao (ed.), Proceedings of the Twentieth International Conference on Artificial Intelligence and Law. Association for Computing Machinery (ACM), New York, pp. 504-505, 20th International Conference on Artificial Intelligence and Law, ICAIL 2025, Chicago, Illinois, United States, 16/06/25. https://doi.org/10.1145/3769126.3769196

A Demonstration of a Semi-Structured Legal Reasoning Framework. / Westermann, Hannes.
Proceedings of the Twentieth International Conference on Artificial Intelligence and Law. ed. / Juliano Maranhao. New York: Association for Computing Machinery (ACM), 2026. p. 504-505.

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceeding › Academic › peer-review

TY - GEN

T1 - A Demonstration of a Semi-Structured Legal Reasoning Framework

AU - Westermann, Hannes

PY - 2026/1/13

Y1 - 2026/1/13

N2 - Legal reasoning strikes a balance between structured elements (i.e. legal criteria and their connections) and unstructured elements (i.e. about of the applicability of open-textured legal terms). Expert systems perform well on the former task, while large language models offer significant potential in the latter style of reasoning. In this demonstration, we present the DALLMA framework, which enables the combination of these two approaches, for semi-structured reasoning. This approach has the potential to assist in many legal reasoning and drafting tasks, while reducing the risks of hallucinations, with important implications for e.g. access to justice.

AB - Legal reasoning strikes a balance between structured elements (i.e. legal criteria and their connections) and unstructured elements (i.e. about of the applicability of open-textured legal terms). Expert systems perform well on the former task, while large language models offer significant potential in the latter style of reasoning. In this demonstration, we present the DALLMA framework, which enables the combination of these two approaches, for semi-structured reasoning. This approach has the potential to assist in many legal reasoning and drafting tasks, while reducing the risks of hallucinations, with important implications for e.g. access to justice.

KW - access to justice

KW - forms

KW - Generative AI

KW - Large Language Models

KW - legal reasoning

U2 - 10.1145/3769126.3769196

DO - 10.1145/3769126.3769196

M3 - Conference article in proceeding

SP - 504

EP - 505

BT - Proceedings of the Twentieth International Conference on Artificial Intelligence and Law

A2 - Maranhao, Juliano

PB - Association for Computing Machinery (ACM)

CY - New York

T2 - 20th International Conference on Artificial Intelligence and Law, ICAIL 2025

Y2 - 16 June 2025 through 20 June 2025

ER -

A Demonstration of a Semi-Structured Legal Reasoning Framework

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this