# Large Language Models as Tax Attorneys: A Case Study in Legal Capabilities Emergence

arXiv: https://arxiv.org/abs/2306.07075 · HTML: https://mlsanity.com/paper/2306.07075/

## Key facts

- Cited by 42 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 55 references that are in the map.
- First posted on arXiv 12 Jun 2023.

## Builds on (most cited first, 30 of 34)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [Mastering Diverse Domains through World Models](https://mlsanity.com/paper/2301.04104/) (2023)
- [Measuring and Narrowing the Compositionality Gap in Language Models](https://mlsanity.com/paper/2210.03350/) (2022)
- [In-Context Retrieval-Augmented Language Models](https://mlsanity.com/paper/2302.00083/) (2023)
- [A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT](https://mlsanity.com/paper/2302.11382/) (2023)
- [Large Dual Encoders Are Generalizable Retrievers](https://mlsanity.com/paper/2112.07899/) (2021)
- [Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents](https://mlsanity.com/paper/2302.01560/) (2023)
- [Language Models can Solve Computer Tasks](https://mlsanity.com/paper/2303.17491/) (2023)
- [Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedback](https://mlsanity.com/paper/2302.12813/) (2023)
- [Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLP](https://mlsanity.com/paper/2212.14024/) (2022)
- [Data Contamination: From Memorization to Exploitation](https://mlsanity.com/paper/2203.08242/) (2022)
- [Grounding Large Language Models in Interactive Environments with Online Reinforcement Learning](https://mlsanity.com/paper/2302.02662/) (2023)
- [Foundation Models for Decision Making: Problems, Methods, and Opportunities](https://mlsanity.com/paper/2303.04129/) (2023)
- [Active Prompting with Chain-of-Thought for Large Language Models](https://mlsanity.com/paper/2302.12246/) (2023)
- [DocPrompting: Generating Code by Retrieving the Docs](https://mlsanity.com/paper/2207.05987/) (2022)
- [Compositional Exemplars for In-context Learning](https://mlsanity.com/paper/2302.05698/) (2023)
- [We're Afraid Language Models Aren't Modeling Ambiguity](https://mlsanity.com/paper/2304.14399/) (2023)
- [Speak, Memory: An Archaeology of Books Known to ChatGPT/GPT-4](https://mlsanity.com/paper/2305.00118/) (2023)
- [When to Make Exceptions: Exploring Language Models as Accounts of Human Moral Judgment](https://mlsanity.com/paper/2210.01478/) (2022)
- [On the Planning Abilities of Large Language Models (A Critical Investigation with a Proposed Benchmark)](https://mlsanity.com/paper/2302.06706/) (2023)
- [Boosting Theory-of-Mind Performance in Large Language Models via Prompting](https://mlsanity.com/paper/2304.11490/) (2023)
- [Goal Driven Discovery of Distributional Differences via Language Descriptions](https://mlsanity.com/paper/2302.14233/) (2023)
- [Read and Reap the Rewards: Learning to Play Atari with the Help of Instruction Manuals](https://mlsanity.com/paper/2302.04449/) (2023)
- [Bounding the Capabilities of Large Language Models in Open Text Generation with Prompt Constraints](https://mlsanity.com/paper/2302.09185/) (2023)
- [Internet Explorer: Targeted Representation Learning on the Open Web](https://mlsanity.com/paper/2302.14051/) (2023)
- [The AI Index 2022 Annual Report](https://mlsanity.com/paper/2205.03468/) (2022)
- [Evaluating the Robustness of Discrete Prompts](https://mlsanity.com/paper/2302.05619/) (2023)

## Built on by (most cited first, 30 of 42)

- [A Survey on Evaluation of Large Language Models](https://mlsanity.com/paper/2307.03109/) (2023)
- [Large Legal Fictions: Profiling Legal Hallucinations in Large Language Models](https://mlsanity.com/paper/2401.01301/) (2024)
- [FedBiOT: LLM Local Fine-tuning in Federated Learning without Full Model](https://mlsanity.com/paper/2406.17706/) (2024)
- [Dialect prejudice predicts AI decisions about people's character, employability, and criminality](https://mlsanity.com/paper/2403.00742/) (2024)
- [Position: AI Evaluation Should Learn from How We Test Humans](https://mlsanity.com/paper/2306.10512/) (2023)
- [A Fast Optimization View: Reformulating Single Layer Attention in LLM Based on Tensor and SVM Trick, and Solving It in Matrix Multiplication Time](https://mlsanity.com/paper/2309.07418/) (2023)
- [Who is ChatGPT? Benchmarking LLMs' Psychological Portrayal Using PsychoBench](https://mlsanity.com/paper/2310.01386/) (2023)
- [Walking a Tightrope -- Evaluating Large Language Models in High-Risk Domains](https://mlsanity.com/paper/2311.14966/) (2023)
- [RelayAttention for Efficient Large Language Model Serving with Long System Prompts](https://mlsanity.com/paper/2402.14808/) (2024)
- [PertEval: Unveiling Real Knowledge Capacity of LLMs with Knowledge-Invariant Perturbations](https://mlsanity.com/paper/2405.19740/) (2024)
- [LLMs as Writing Assistants: Exploring Perspectives on Sense of Ownership and Reasoning](https://mlsanity.com/paper/2404.00027/) (2024)
- [Evaluating AI for Law: Bridging the Gap with Open-Source Solutions](https://mlsanity.com/paper/2404.12349/) (2024)
- [ArabLegalEval: A Multitask Benchmark for Assessing Arabic Legal Knowledge in Large Language Models](https://mlsanity.com/paper/2408.07983/) (2024)
- [BLT: Can Large Language Models Handle Basic Legal Text?](https://mlsanity.com/paper/2311.09693/) (2023)
- [Unifying Corroborative and Contributive Attributions in Large Language Models](https://mlsanity.com/paper/2311.12233/) (2023)
- [Beyond Words: On Large Language Models Actionability in Mission-Critical Risk Analysis](https://mlsanity.com/paper/2406.10273/) (2024)
- [Implicit Bias in LLMs: A Survey](https://mlsanity.com/paper/2503.02776/) (2025)
- [Lawma: The Power of Specialization for Legal Annotation](https://mlsanity.com/paper/2407.16615/) (2024)
- [Large Language Models and Emergence: A Complex Systems Perspective](https://mlsanity.com/paper/2506.11135/) (2025)
- [Enhancing Logical Reasoning in Large Language Models to Facilitate Legal Applications](https://mlsanity.com/paper/2311.13095/) (2023)
- [It Cannot Be Right If It Was Written by AI: On Lawyers' Preferences of Documents Perceived as Authored by an LLM vs a Human](https://mlsanity.com/paper/2407.06798/) (2024)
- [Towards Trustworthy Legal AI through LLM Agents and Formal Reasoning](https://mlsanity.com/paper/2511.21033/) (2025)
- [Large Language Models in Cryptocurrency Securities Cases: Can a GPT Model Meaningfully Assist Lawyers?](https://mlsanity.com/paper/2308.06032/) (2023)
- [Retrieval-Augmented Chain-of-Thought in Semi-structured Domains](https://mlsanity.com/paper/2310.14435/) (2023)
- [Focus Agent: LLM-Powered Virtual Focus Group](https://mlsanity.com/paper/2409.01907/) (2024)
- [Adaptive Collaboration of Arena-Based Argumentative LLMs for Explainable and Contestable Legal Reasoning](https://mlsanity.com/paper/2602.18916/) (2026)
- [Balancing Exploration and Exploitation in LLM using Soft RLLF for Enhanced Negation Understanding](https://mlsanity.com/paper/2403.01185/) (2024)
- [Software Engineering Methods For AI-Driven Deductive Legal Reasoning](https://mlsanity.com/paper/2404.09868/) (2024)
- [MoPEFT: A Mixture-of-PEFTs for the Segment Anything Model](https://mlsanity.com/paper/2405.00293/) (2024)
- [Taxation Perspectives from Large Language Models: A Case Study on Additional Tax Penalties](https://mlsanity.com/paper/2503.03444/) (2025)

## Abstract (arXiv)

Better understanding of Large Language Models' (LLMs) legal analysis abilities can contribute to improving the efficiency of legal services, governing artificial intelligence, and leveraging LLMs to identify inconsistencies in law. This paper explores LLM capabilities in applying tax law. We choose this area of law because it has a structure that allows us to set up automated validation pipelines across thousands of examples, requires logical reasoning and maths skills, and enables us to test LLM capabilities in a manner relevant to real-world economic lives of citizens and companies. Our experiments demonstrate emerging legal understanding capabilities, with improved performance in each subsequent OpenAI model release. We experiment with retrieving and utilising the relevant legal authority to assess the impact of providing additional legal context to LLMs. Few-shot prompting, presenting examples of question-answer pairs, is also found to significantly enhance the performance of the most advanced model, GPT-4. The findings indicate that LLMs, particularly when combined with prompting enhancements and the correct legal texts, can perform at high levels of accuracy but not yet at expert tax lawyer levels. As LLMs continue to advance, their ability to reason about law autonomously could have significant implications for the legal profession and AI governance.