Introduction

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.

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.

By tackling the challenges of multilingual semantic understanding, domain adaptation, and regulatory alignment, the RegCom task contributes toward building intelligent, scalable tools for corporate sustainability analysis and oversight.

Previous Tasks:

[1] PromiseEval-2025 @ SemEval: https://sites.google.com/view/promiseeval/

[2] Multi-Lingual ESG Issue Identification: https://aclanthology.org/2023.finnlp-1.11/

[3] Multi-Lingual ESG Impact Type Identification: https://aclanthology.org/2023.finnlp-2.6/

[4] Multi-Lingual ESG Impact Duration Inference: https://aclanthology.org/2024.finnlp-1.22/

Contact: https://groups.google.com/g/regcom