Work

An LLM Agentic Approach for Legal-Critical Software: A Case Study for Tax Prep Software

Year: 2026

Type: conference-paper

Abstract: As Large Language Models (LLMs) continue to advance in their ability to process both natural and programming languages, they show promise for translation tasks in domains with strict compliance requirements. Yet ensuring consistency in legally critical settings remains challenging due to inherent limitations such as natural language ambiguity and the tendency to hallucinate. This paper explores an agentic approach that leverages LLMs for the development of legal-critical software. We use U.S. federal tax software as a representative case study, where natural language tax code must be translated precisely into executable logic.

Source: IEEE/ACM International Conference on Software Engineering (ICSE)

DOI: 10.1145/3744916.3764575

Authors: Sina Gogani Khiabani, Ashutosh Trivedi, Diptikalyan Saha, Saeid Tizpaz-Niari

Institutions: University of Illinois Chicago, University of Colorado Boulder, IBM (India)

Language: English

Topic: Artificial Intelligence in Law

Subfield: Political Science and International Relations

Field: Social Sciences

Domain: Social Sciences

Open Access status: hybrid

Funder: National Science Foundation

Awards: Collaborative Research: DASS: Assessing Accountability of Tax Preparation Software Systems, Collaborative Research: DASS: Assessing Accountability of Tax Preparation Software Systems, Collaborative Research: DASS: Assessing Accountability of Tax Preparation Software Systems