LLM-Tax-Abuse
Code and US tax-strategy data from the paper on whether LLMs can identify and generate tax abuse.
What it does
Code and data from the paper Can LLMs Identify Tax Abuse?: Python scripts that test whether a language model can verify, complete and generate US tax-minimisation strategies, then grade the answers. It needs Python and an OpenAI API key with batch API access. Only 5 of the 36 expert-written strategy files are published, to keep the rest out of model training; no licence is stated.
Licence unknown: we found no licence we could recognise. Check with the maintainers before you reuse the code.
Where it fits on the map
Similar projects
Of the same kind, for a shared jurisdiction or tax area. Not a ranking.
- harvey-labs (Legal Agent Benchmark)Legal Agent Benchmark: 2,010 legal tasks with documents and rubrics and a Python harness; 34 tasks are tax.
- SARAStatutory reasoning benchmark built on the US Internal Revenue Code.
- TaxCalcBenchBenchmark that tests frontier AI models on US tax return calculations.
- TaxBench114 expert-written US tax questions with grading rubrics for testing LLMs; 19 touch transfer pricing or s.482.Inactive since 2025
Maintain this project?
Link to this page from your README, so readers find the facts, the notes and where it fits. The badge is a small SVG served from this site.
[](https://tax-oss.com/projects/llm-tax-abuse/)