LLM-assisted formalization for deterministic detection of statutory inconsistency in tax law
This study introduces a hybrid neuro-symbolic framework that achieves deterministic detection of statutory inconsistency in complex law. We use the U.S. Internal Revenue Code (IRC) for our investigation because its complexity makes it a fertile domain for identifying conflicts. Our research advances a solution for detecting inconsistent provisions by combining Large Language Models (LLMs) with a symbolic reasoner. To evaluate this approach, we conducted experiments using GPT-4o, GPT-5, and Prolo
Record details
Published: 10 July 2026
Source: Artificial Intelligence and Law
Category: Research
Topics: Regulation · Finance, VC & PE
Retrieved: 14 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
Knowing the Rules Is Not Enough: Student Regulatory Awareness and Use of GenAI in Higher Education
arXiv · 16 May 2026
From GPT-3 to GPT-5: Mapping their capabilities, scope, limitations, and consequences
arXiv · 11 April 2026
Why are OpenAI and Anthropic cheering on regulation in Australia? The answer has global reach
The Guardian · 22 July 2026
Dario Amodei, CEO de Anthropic: "Mythos es un arma total. Deberías necesitar una licencia de armas para usarlo"
Xataka (ES) · 24 July 2026
Joshua Kushner’s Thrive Capital Discloses $215 Million Amazon Stake
The Next Web AI · 14 August 2026
Geopolitical alignment: Endorsement effects in large language models
arXiv · 10 July 2026
How to cite this record
ethics.ai (10 July 2026), “LLM-assisted formalization for deterministic detection of statutory inconsistency in tax law,” evidence record 1997, https://ethics.ai/record/1997 (originally published by Artificial Intelligence and Law).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.