RegCom: Multinational, Multilingual, Multi-Industry Regulatory Compliance Checking

Attached to NTCIR-19 2026 • December 8th-10th, 2026 • Tokyo, Japan
Shared Task website: https://sites.google.com/view/ntcir19regcom/regcom?authuser=0

Motivation

The RegCom (Regulatory Compliance) task is a pilot shared task under NTCIR-19 that aims to evaluate and advance automatic systems for regulatory compliance checking of ESG (Environmental, Social, and Governance) reports. In light of increasing regulatory demands and the global push for transparent and standardized ESG disclosure, organizations are now under pressure to ensure their reports adhere to recognized frameworks such as the Sustainability Accounting Standards Board (SASB) guidelines.

However, ESG reports often vary greatly across regions, languages, industries, and organizational scales. They are typically multilingual, semi-structured, and contain a mix of text and visual elements—making manual compliance checks time-consuming, expensive, and inconsistent. The RegCom task addresses this issue by encouraging the development of automated systems capable of understanding, interpreting, and evaluating ESG report content across six languages and six countries.

Focus & Themes

Topics of interest include (but are not limited to):
1. Multimodal Information Retrieval
2. Alignment with referential data
3. Corporate, policy, and societal accountability via IR/NLP
4. Datasets, benchmarks, and evaluation protocols
5. Responsible/Trustworthy AI for accountability & integrity

Task 1: Multinational, Multilingual, Multi-Industry Regulatory Compliance Checking
This task invites participants to design systems that align ESG content with SASB metrics, verifying whether the necessary disclosures are present and correctly formatted. The goal is to simulate real-world compliance review settings through two subtasks: (1) full-report analysis and (2) single-page verification. Both subtasks are grounded in multilingual, multimodal, and multi-industry contexts, offering a rich and practical benchmark for researchers and practitioners in NLP, IR, and legal-tech.

Task 2: Reporting Template Evidence Linking for Modern Slavery Statements (AIMS-TEL)
AIMS-TEL is a pilot task focusing on explainable regulatory document understanding in modern slavery disclosures. Participants must assess whether required reporting elements from the International Reporting Template (Levels 1–2) are addressed in corporate statements published in response to the Modern Slavery Acts, and link each prediction to supporting evidence in the text. Systems should classify each template element as {present / partially present / absent}, provide rationales and spans, and estimate uncertainty. An optional subtask encourages template auto-population, gap detection, and longitudinal analysis (e.g., comparing promised vs. delivered actions across reporting years).

Task 3: Aspect–Action Analysis with Cross-Category Generalization (A3CG)
The A3CG (Aspect–Action Analysis with Cross-Category Generalization) task focuses on analyzing sustainability disclosures in corporate ESG (Environmental, Social, and Governance) reports. Companies often present their sustainability performance in vague or exaggerated ways (a practice known as greenwashing), which makes it difficult to interpret whether reported claims reflect meaningful action. The task addresses this challenge by requiring systems to clarify sustainability statements through explicit linking of aspects (what is being addressed) and actions (how it is being addressed).


Important Dates of 2026

May 1: Test Set Release
June 1: Task Registration Due
June 15: Participants' Results Submission Due
August 1: Evaluation Result Release & Draft Task Overview Paper Release
September 1: Participants' Papers Submission Due
November 1: Camera-ready Paper
December 8th-10th: NTCIR-19 Conference in NII, Tokyo, Japan

How to Submit

Fill in the registration form. Details and registration form are available on the RegCom website.

We look forward to your submissions and to building a community around accountability-driven IR & NLP!

Organising Committee

Yohei Seki - University of Tsukuba, Japan
Juyeon Kang - 3DS Outscale, France
Anaïs Lhuissier - 3DS Outscale, France
Dittaya Wanvarie - Chulalongkorn University, Thailand
Min-Yuh Day - National Taipei University, Taiwan
Atsushi Keyaki - Hitotsubashi University, Japan
Yuriko Nakao - Kansai University, Japan
Tomoki Kera - Hitotsubashi University, Japan
Adriana E. Bora - Queensland University of Technology, Australia
Keane Ong Wei Yang - National University of Singapore, Singapore and Massachusetts Institute of Technology, USA
Hsin-Hsi Chen - National Taiwan University, Taiwan
Hiroya Takamura - AIST, Japan
Chung-Chi Chen - AIST, Japan

Contact: c.c.chen@acm.org (for general enquiries)