@inproceedings{moore-etal-2026-oblex26,
title = "{O}bl{E}x26: A Multi-Jurisdictional Benchmark for Structured Obligation Extraction from Anti-Money Laundering Regulations",
author = "Moore, Philip and
Bandi, Giovanni and
Horstmann, Tim Luka and
Moore, Russell and
Wardrop, Robert H. and
Buttery, Paula",
editor = "Aletras, Nikolaos and
Chalkidis, Ilias and
Barrett, Leslie and
Goanț{\u{a}}, C{\u{a}}t{\u{a}}lina and
Preoțiuc-Pietro, Daniel and
Spanakis, Gerasimos and
Xu, Shanshan",
booktitle = "Proceedings of the Natural Legal Language Processing Workshop 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.nllp-1.4/",
pages = "14--28",
ISBN = "979-8-89176-494-1",
abstract = "Anti-money laundering and counter-terrorism financing (AML/CFT) regulations impose complex obligations on financial institutions. Auditing these obligations requires thousands of hours of manual review by legal experts, yet automated structured obligation extraction remains underexplored. In this paper we: 1) Introduce OblEx26, the first multi-jurisdictional benchmarking dataset designed for evaluating structured obligation extraction from regulatory documents. The dataset contains 48 expert-annotated documents spanning 14 jurisdictions, consisting of 43 documents in English and 5 in Brazilian Portuguese and Mandarin. Grounded in Hohfeldian legal theory and deontic logic, each obligation is decomposed into six components ``Holder'', ``Type'', ``Beneficiary'', ``Antecedent'', ``Consequent'', ``Source / Legal Channel'' and is anchored to exact quotes, enabling verifiable provenance; 2) Compare four open-weight methods for structured obligation extraction that can run privately on consumer-grade hardware: token-classification encoders; a joint classification and obligation-linking architecture; zero-shot with LLMs; and fine-tuned SLMs. Our fine-tuned SLM Qwen3.5-27B achieves a soft-match F1 score of 0.728, with 0.991 exact quote anchoring on English language data, and 0.659 F1 with 1.000 anchoring when used zero-shot on the cross-lingual data. Fine-tuned SLMs substantially outperform zero-shot LLMs and encoder-based approaches, establishing a strong baseline for automated legal compliance. OblEx26 evaluation data is publicly released."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="moore-etal-2026-oblex26">
<titleInfo>
<title>OblEx26: A Multi-Jurisdictional Benchmark for Structured Obligation Extraction from Anti-Money Laundering Regulations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Philip</namePart>
<namePart type="family">Moore</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giovanni</namePart>
<namePart type="family">Bandi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tim</namePart>
<namePart type="given">Luka</namePart>
<namePart type="family">Horstmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Russell</namePart>
<namePart type="family">Moore</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robert</namePart>
<namePart type="given">H</namePart>
<namePart type="family">Wardrop</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paula</namePart>
<namePart type="family">Buttery</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Natural Legal Language Processing Workshop 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nikolaos</namePart>
<namePart type="family">Aletras</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ilias</namePart>
<namePart type="family">Chalkidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leslie</namePart>
<namePart type="family">Barrett</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cătălina</namePart>
<namePart type="family">Goanță</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Preoțiuc-Pietro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gerasimos</namePart>
<namePart type="family">Spanakis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shanshan</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-494-1</identifier>
</relatedItem>
<abstract>Anti-money laundering and counter-terrorism financing (AML/CFT) regulations impose complex obligations on financial institutions. Auditing these obligations requires thousands of hours of manual review by legal experts, yet automated structured obligation extraction remains underexplored. In this paper we: 1) Introduce OblEx26, the first multi-jurisdictional benchmarking dataset designed for evaluating structured obligation extraction from regulatory documents. The dataset contains 48 expert-annotated documents spanning 14 jurisdictions, consisting of 43 documents in English and 5 in Brazilian Portuguese and Mandarin. Grounded in Hohfeldian legal theory and deontic logic, each obligation is decomposed into six components “Holder”, “Type”, “Beneficiary”, “Antecedent”, “Consequent”, “Source / Legal Channel” and is anchored to exact quotes, enabling verifiable provenance; 2) Compare four open-weight methods for structured obligation extraction that can run privately on consumer-grade hardware: token-classification encoders; a joint classification and obligation-linking architecture; zero-shot with LLMs; and fine-tuned SLMs. Our fine-tuned SLM Qwen3.5-27B achieves a soft-match F1 score of 0.728, with 0.991 exact quote anchoring on English language data, and 0.659 F1 with 1.000 anchoring when used zero-shot on the cross-lingual data. Fine-tuned SLMs substantially outperform zero-shot LLMs and encoder-based approaches, establishing a strong baseline for automated legal compliance. OblEx26 evaluation data is publicly released.</abstract>
<identifier type="citekey">moore-etal-2026-oblex26</identifier>
<location>
<url>https://aclanthology.org/2026.nllp-1.4/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>14</start>
<end>28</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T OblEx26: A Multi-Jurisdictional Benchmark for Structured Obligation Extraction from Anti-Money Laundering Regulations
%A Moore, Philip
%A Bandi, Giovanni
%A Horstmann, Tim Luka
%A Moore, Russell
%A Wardrop, Robert H.
%A Buttery, Paula
%Y Aletras, Nikolaos
%Y Chalkidis, Ilias
%Y Barrett, Leslie
%Y Goanță, Cătălina
%Y Preoțiuc-Pietro, Daniel
%Y Spanakis, Gerasimos
%Y Xu, Shanshan
%S Proceedings of the Natural Legal Language Processing Workshop 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-494-1
%F moore-etal-2026-oblex26
%X Anti-money laundering and counter-terrorism financing (AML/CFT) regulations impose complex obligations on financial institutions. Auditing these obligations requires thousands of hours of manual review by legal experts, yet automated structured obligation extraction remains underexplored. In this paper we: 1) Introduce OblEx26, the first multi-jurisdictional benchmarking dataset designed for evaluating structured obligation extraction from regulatory documents. The dataset contains 48 expert-annotated documents spanning 14 jurisdictions, consisting of 43 documents in English and 5 in Brazilian Portuguese and Mandarin. Grounded in Hohfeldian legal theory and deontic logic, each obligation is decomposed into six components “Holder”, “Type”, “Beneficiary”, “Antecedent”, “Consequent”, “Source / Legal Channel” and is anchored to exact quotes, enabling verifiable provenance; 2) Compare four open-weight methods for structured obligation extraction that can run privately on consumer-grade hardware: token-classification encoders; a joint classification and obligation-linking architecture; zero-shot with LLMs; and fine-tuned SLMs. Our fine-tuned SLM Qwen3.5-27B achieves a soft-match F1 score of 0.728, with 0.991 exact quote anchoring on English language data, and 0.659 F1 with 1.000 anchoring when used zero-shot on the cross-lingual data. Fine-tuned SLMs substantially outperform zero-shot LLMs and encoder-based approaches, establishing a strong baseline for automated legal compliance. OblEx26 evaluation data is publicly released.
%U https://aclanthology.org/2026.nllp-1.4/
%P 14-28
Markdown (Informal)
[OblEx26: A Multi-Jurisdictional Benchmark for Structured Obligation Extraction from Anti-Money Laundering Regulations](https://aclanthology.org/2026.nllp-1.4/) (Moore et al., NLLP 2026)
ACL