# From Statute to Control Flow: Span-Grounded Deontic Trees for Defeasible Scope Parsing

arXiv: https://arxiv.org/abs/2606.08932 · HTML: https://mlsanity.com/paper/2606.08932/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 28 references that are in the map.
- First posted on arXiv 8 Jun 2026.

## Builds on (most cited first, 13 of 13)

- [LexGLUE: A Benchmark Dataset for Legal Language Understanding in English](https://mlsanity.com/paper/2110.00976/) (2021)
- [Large Legal Fictions: Profiling Legal Hallucinations in Large Language Models](https://mlsanity.com/paper/2401.01301/) (2024)
- [Interpretation of Natural Language Rules in Conversational Machine Reading](https://mlsanity.com/paper/1809.01494/) (2018)
- [A Dataset for Statutory Reasoning in Tax Law Entailment and Question Answering](https://mlsanity.com/paper/2005.05257/) (2020)
- [FinTextQA: A Dataset for Long-form Financial Question Answering](https://mlsanity.com/paper/2405.09980/) (2024)
- [LEXam: Benchmarking Legal Reasoning on 340 Law Exams](https://mlsanity.com/paper/2505.12864/) (2025)
- [Natural Language Processing for the Legal Domain: A Survey of Tasks, Datasets, Models, and Challenges](https://mlsanity.com/paper/2410.21306/) (2024)
- [LexEval: A Comprehensive Chinese Legal Benchmark for Evaluating Large Language Models](https://mlsanity.com/paper/2409.20288/) (2024)
- [Factoring Statutory Reasoning as Language Understanding Challenges](https://mlsanity.com/paper/2105.07903/) (2021)
- ["You don't need a university degree to comprehend data protection this way": LLM-Powered Interactive Privacy Policy Assessment](https://mlsanity.com/paper/2503.03587/) (2025)
- [Compliance-to-Code: Enhancing Financial Compliance Checking via Code Generation](https://mlsanity.com/paper/2505.19804/) (2025)
- [Towards Exception Safety Code Generation with Intermediate Representation Agents Framework](https://mlsanity.com/paper/2410.06949/) (2024)
- [Critical or Compliant? The Double-Edged Sword of Reasoning in Chain-of-Thought Explanations](https://mlsanity.com/paper/2511.12001/) (2025)

## Built on by (most cited first, 1 of 1)

- [When Evidence Changes the Subject: Subject-Typed Claim Licensing for Learned Routing](https://mlsanity.com/paper/2609.33505/) (2026)

## Abstract (arXiv)

Rule-following agents tasked with executing policies and regulations often fail via Silent Scope Omission (SSO): a model applies a general rule but silently drops nested exceptions or counter-exceptions, producing outputs that appear compliant yet break on important edge cases. Although such failures are often framed as an agentic-systems problem, the underlying bottleneck is statutory and policy understanding, a capability typically studied in legal NLP. However, most existing legal NLP benchmarks emphasize end-task outcomes, which can overlook the structural omissions that cause SSO. To diagnose and mitigate SSO, we introduce NormBench, a benchmark of 2,290 provisions spanning Chinese (laws and local policies), English (U.S. tax law, GDPR, and corporate policies), and cross-lingual settings, designed for defeasible scope parsing: identifying precisely which clause overrides which. NormBench uses Span-Grounded Deontic Trees (SG-DT), a compiler-style intermediate representation that anchors every logical branch to source spans and requires explicit exclusion guards, enabling deterministic compilation and audit. Evaluations of frontier LLMs reveal two recurring pathologies: (1) Recursion Decay, where performance drops sharply as defeater depth increases, and (2) an Auditability Trap, where models retrieve relevant spans but fail to assemble correct control flow. Using SG-DT as a constrained intermediate output improves whole-tree fidelity and defeater recovery, and downstream experiments show that its utility is mechanism-specific: gains concentrate on exception-active, SSO-prone cases, while aggregate accuracy can be mixed when the added structure is unnecessary or parser fidelity is low.