大模型能发现美国避税策略，还能自动生成完整方案。
Can LLMs Identify Tax Abuse?
- 用大模型解析和验证真实税务策略，填补不完整信息
- 在真实税务法规中发现全新避税方法，超越人类专家水平
- 适合关注法律推理与合规技术的政策制定者和研究者
我们研究大语言模型识别和分析美国税收筹划策略的能力。该现实领域对经验丰富的税务专家也是挑战，进展有助于减少高净值纳税人合理避税导致的税收损失。评估最先进大模型在三项任务上的表现：（1）解读并验证税务策略；（2）补全部分缺失的策略；（3）从零生成完整、端到端的税务策略。此领域对大模型推理研究极具吸引力：不同于合成难题或科学推理任务，美国税法包含数十万页的成文法、判例和行政指南，且持续更新。值得注意的是，基于大模型的推理首次发现了全新的避税策略，凸显其在税务监管领域变革性潜力。
原文摘要 · Abstract (English)
We investigate whether large language models can discover and analyze U.S. tax-minimization strategies. This real-world domain challenges even seasoned human experts, and progress can reduce tax revenue lost from well-advised, wealthy taxpayers. We evaluate the most advanced LLMs on their ability to (1) interpret and verify tax strategies, (2) fill in gaps in partially specified strategies, and (3) generate complete, end-to-end strategies from scratch. This domain should be of particular interest to the LLM reasoning community: unlike synthetic challenge problems or scientific reasoning tasks, U.S. tax law involves navigating hundreds of thousands of pages of statutes, case law, and administrative guidance, all updated regularly. Notably, LLM-based reasoning identified an entirely novel tax strategy, highlighting these models' potential to revolutionize tax agencies' fight against tax abuse.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。