# Language Models and Logic Programs for Trustworthy Tax Reasoning

arXiv: https://arxiv.org/abs/2508.21051 · HTML: https://mlsanity.com/paper/2508.21051/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 14 of its 61 references that are in the map.
- First posted on arXiv 28 Aug 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)

## Builds on (most cited first, 14 of 14)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [DeepSeek-V3 Technical Report](https://mlsanity.com/paper/2412.19437/) (2024)
- [LLMs Can Easily Learn to Reason from Demonstrations Structure, not content, is what matters!](https://mlsanity.com/paper/2502.07374/) (2025)
- [Inverse Scaling in Test-Time Compute](https://mlsanity.com/paper/2507.14417/) (2025)
- [Beyond GPT-5: Making LLMs Cheaper and Better via Performance-Efficiency Optimized Routing](https://mlsanity.com/paper/2508.12631/) (2025)
- [Large language models can learn and generalize steganographic chain-of-thought under process supervision](https://mlsanity.com/paper/2506.01926/) (2025)
- [Towards Robust Legal Reasoning: Harnessing Logical LLMs in Law](https://mlsanity.com/paper/2502.17638/) (2025)
- [Rank-K: Test-Time Reasoning for Listwise Reranking](https://mlsanity.com/paper/2505.14432/) (2025)
- [OpenAI Cribbed Our Tax Example, But Can GPT-4 Really Do Tax?](https://mlsanity.com/paper/2309.09992/) (2023)
- [Tax Knowledge Graph for a Smarter and More Personalized TurboTax](https://mlsanity.com/paper/2009.06103/) (2020)
- [Can LLMs Identify Tax Abuse?](https://mlsanity.com/paper/2508.20097/) (2025)

## Built on by (most cited first, 4 of 4)

- [Know Your Limits : On the Faithfulness of LLMs as Solvers and Autoformalizers in Legal Reasoning](https://mlsanity.com/paper/2606.16118/) (2026)
- [Reasoners or Translators? Contamination-aware Evaluation and Neuro-Symbolic Robustness in Tax Law](https://mlsanity.com/paper/2605.16052/) (2026)
- [Solving versus Verifying: Catching Contradictions in Tax Reasoning Systems](https://mlsanity.com/paper/2609.05928/) (2026)
- [Mining Legal Arguments in U.S. Corporate Case Law](https://mlsanity.com/paper/2609.25441/) (2026)

## Abstract (arXiv)

According to the United States Internal Revenue Service, ``the average American spends 270 and 13 hours filing their taxes''. Even beyond the U.S., tax filing requires complex reasoning, combining application of overlapping rules with numerical calculations. Because errors can incur costly penalties, any automated system must deliver high accuracy and auditability, making modern large language models (LLMs) poorly suited for this task. We propose an approach that integrates LLMs with a symbolic solver to calculate tax obligations. We evaluate variants of this system on the challenging StAtutory Reasoning Assessment (SARA) dataset, and include a novel method for estimating the cost of deploying such a system based on real-world penalties for tax errors. We further show how combining up-front translation of plain-text rules into formal logic programs, combined with intelligently retrieved exemplars for formal case representations, can dramatically improve performance on this task and reduce costs to well below real-world averages. Our results demonstrate the effectiveness of applying semantic parsing methods to statutory reasoning, and show promising economic feasibility of neuro-symbolic architectures for increasing access to reliable tax assistance.