Large language models as tax attorneys: a case study in legal capabilities emergence
Open accessThe DOI matches its Crossref record; 20 of the 20 references it cites were found in a registry or an index.
Abstract
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 using 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. This article is part of the theme issue ‘A complexity science approach to law and governance’.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Toolformer: Language Models Can Teach Themselves to Use Tools
Schick, T., Dwivedi-Yu, J., Dessì, R., Raileanu, R., Lomeli, M., Zettlemoyer, L., Cancedda, N., & Scialom, T. (2023) · arXiv · doi:10.48550/arxiv.2302.04761 · Cited by 1,150
Reflexion: Language Agents with Verbal Reinforcement Learning
Shinn, N., Cassano, F., Berman, E., Gopinath, A., Narasimhan, K., & Yao, S. (2023) · arXiv · doi:10.48550/arxiv.2303.11366 · Cited by 1,087
G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment
Liu, Y., Iter, D., Xu, Y., Wang, S., Xu, R., & Zhu, C. (2023) · arXiv · doi:10.48550/arxiv.2303.16634 · Cited by 948
G-Eval: NLG Evaluation using Gpt-4 with Better Human Alignment
Liu, Y., Iter, D., Xu, Y., Wang, S., Xu, R., & Zhu, C. (2023) · Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2023.emnlp-main.153 · Cited by 948
A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT
White, J., Fu, Q., Hays, S., Sandborn, M., Olea, C., Gilbert, H., Elnashar, A., Spencer-Smith, J., & Schmidt, D. C. (2023) · arXiv · doi:10.48550/arxiv.2302.11382 · Cited by 838
ReAct: Synergizing Reasoning and Acting in Language Models
Yao, S., Zhao, J., Yu, D., Du, N., Shafran, I., Narasimhan, K., & Cao, Y. (2022) · arXiv · doi:10.48550/arxiv.2210.03629 · Cited by 608
In-Context Retrieval-Augmented Language Models
Ram, O., Levine, Y., Dalmedigos, I., Muhlgay, D., Shashua, A., Leyton-Brown, K., & Shoham, Y. (2023) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00605 · Cited by 449 · cited 1×
“[57] present a simpler alternative to Retrieval-Augmented Language Modeling (RALM): in-context RALM, where grounding documents are incorporated into the LLM’s input without modifying its architecture.”
MethodHuman-level play in the game of Diplomacy by combining language models with strategic reasoning
Meta Fundamental AI Research Diplomacy Team (FAIR)†, Bakhtin, A., Brown, N., Dinan, E., Farina, G., Flaherty, C., Fried, D., Goff, A., Gray, J., Hu, H., et al. (2022) · Science · doi:10.1126/science.ade9097 · Cited by 241
(2022) · doi:10.18653/v1/2022.emnlp-main.669 · Cited by 177
Augmented Language Models: a Survey
Mialon, G., Dessì, R., Lomeli, M., Nalmpantis, C., Pasunuru, R., Raileanu, R., Rozière, B., Schick, T., Dwivedi-Yu, J., Celikyilmaz, A., et al. (2023) · arXiv · doi:10.48550/arxiv.2302.07842 · Cited by 160
Cited by
AI generates covertly racist decisions about people based on their dialect
Hofmann, V., Kalluri, P. R., Jurafsky, D., & King, S. (2024) · Nature · doi:10.1038/s41586-024-07856-5 · Cited by 233
Testing AI on language comprehension tasks reveals insensitivity to underlying meaning
Dentella, V., Günther, F., Murphy, E., Marcus, G., & Leivada, E. (2024) · Scientific Reports · doi:10.1038/s41598-024-79531-8 · Cited by 54
Large language models: an overview of foundational architectures, recent trends, and a new taxonomy
Mienye, I. D., Jere, N., Obaido, G., Ogunruku, O. O., Esenogho, E., & Modisane, C. (2025) · Discover Applied Sciences · doi:10.1007/s42452-025-07668-w · Cited by 46
Prompt Cache: Modular Attention Reuse for Low-Latency Inference
Gim, I., Chen, G., Lee, S.-S., Sarda, N., Khandelwal, A., & Zhong, L. (2023) · arXiv · doi:10.48550/arxiv.2311.04934 · Cited by 18
Sparks of Large Audio Models: A Survey and Outlook
Latif, S., Shoukat, M., Shamshad, F., Usama, M., Ren, Y., Cuayáhuitl, H., Wang, W., Zhang, X., Togneri, R., Cambria, E., et al. (2023) · arXiv · doi:10.48550/arxiv.2308.12792 · Cited by 17
“[46] 2023 ✓ ✗ Law Examines LLM’s proficiency in tax law application, noting improvements in newer models compared to older ones.”
Background
Metadata
- Authors
- Nay, J. J., Karamardian, D., Lawsky, S. B., Tao, W., Bhat, M., Jain, R., Lee, A. T., Choi, J. H., & Kasai, J.
- Venue
- Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences
- Publisher
- The Royal Society
- Published
- 2024-02-26
- Volume
- 382
- Issue
- 2270
- Pages
- 20230159-20230159
- ISSN
- 1364-503X (ISSN-L)
- 1471-2962
- OpenAlex
- W4392477373
- Cited by
- 40
- References
- 20
- FWCI
- 61.12
- Type
- journal article
- Language
- en
- Open access
- hybrid
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Large language models as tax attorneys: a case study in legal capabilities emergence. https://app.cochat.ai/papers/10.1098/rsta.2023.0159
- The paper
- Nay, J. J., Karamardian, D., Lawsky, S. B., Tao, W., Bhat, M., Jain, R., Lee, A. T., Choi, J. H., & Kasai, J. (2024). Large language models as tax attorneys: a case study in legal capabilities emergence. Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences. https://doi.org/10.1098/rsta.2023.0159
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.