Introduction

As the United Nations Sustainable Development Goals (SDGs) and global net-zero policies accelerate, ESG disclosure has become a defining measure of corporate credibility. Yet many sustainability reports still contain vague or unverified claims, highlighting an urgent need for intelligent verification tools—especially for Traditional Chinese ESG texts, where language resources remain limited.
The “ESG Sustainability Commitment Verification Competition 2026” invites you to tackle this real-world challenge. Using the VeriPromiseESG4K Annotated Corpus, built from authentic industry scenarios, participants will develop NLP models that identify sustainability commitments and assess their supporting evidence.

This is an opportunity to apply AI to a high-impact global issue, sharpen your skills in ESG analytics and model development, and contribute to greater transparency and trust in corporate sustainability disclosures. This competition provides 4,000 annotated Traditional Chinese ESG entries drawn from real corporate sustainability reports, forming the VeriPromiseESG4K dataset. Participants will apply AI technology such as natural language processing and large language models to develop NLP models capable of automatically identifying, analyzing, and verifying corporate sustainability commitments.
Participating teams will utilize the “VeriPromiseESG4K Annotated Corpus” to develop Natural Language Processing (NLP) models addressing the following four core tasks and generate prediction results for the test dataset:

• Subtask 1: Commitment Classification
  Determine whether the given text expresses a concrete corporate commitment toward future actions.
• Subtask 2: Timeline Classification
  Based on semantic inference, determine the expected completion timeframe of the identified commitment (calculated from the publication year 2024 of the ESG report).
• Subtask 3: Evidence Identification
  Determine whether the identified commitment sentence is supported by action plans or existing records (e.g., data, methodologies, measures, or any concrete implementation details).
• Subtask 4: Clarity Classification
  If evidence is present, evaluate whether the evidence statement is semantically explicit; easy to understand; free from vague wording (e.g., “continuously advancing,” “striving to improve”).

To facilitate participating teams in successfully initiating their model development projects, the organizer will provide relevant technical support and resources, including:

• Regional Hands-on Workshops:
  Free in-person workshops will be conducted across three regions, accompanied by parallel online sessions. These sessions will provide detailed explanations of the competition information and demonstrate the use of sample code, guiding participants through fundamental hands-on implementation.
• Sample Code and Discussion Forum:
  After teams complete official registration and gain access to the competition platform, the organizer will provide the Sample Code and grant access to the official public discussion forum, where participants may engage in discussions and raise questions.
• Official Inquiry Form:
  If you encounter any questions or difficulties during the competition period and are unable to raise them through the official discussion forum, you may submit your inquiries or concerns via Google Form. Upon submission, the Organizer will provide an official response or appropriate assistance.

Eligibility

1. Student Division:
• Individuals who, from the date of registration until the submission deadline for the competition test set predictions, hold official student status in the Republic of China (Taiwan), are at least 18 years of age, and are currently enrolled in an educational institution at any level are eligible to register for this competition.
• Minors under the age of 18 may participate with the consent of their legal guardian.
• Relevant supporting documentation (such as a photocopy of both sides of a student ID card or an original certificate of enrollment) must be submitted when awarding prizes.
2. General Public Division:

If any team member does not meet the eligibility requirements of the Student Division (including students currently enrolled in institutions outside the Republic of China), the entire team will be classified under the General Public Division.

Registration

1. Each team member must register through the AI CUP Registration System (first-time users may refer to the AI CUP Registration System guide for instructions). Participants must follow the on-screen registration procedures, complete all required information, and finalize team formation to complete competition enrollment. Team names will be automatically assigned by the system; participants are not permitted to choose their own team names.
2. Within 1–2 business days after completing competition enrollment via the AI CUP Registration System, an account activation notice and password for the AIdea Platform will be sent to the participant’s registered email address. After completing the activation steps indicated in the email, all team members may access the AIdea Platform to participate in the competition.
3. If participants are registering as part of a course requirement, they should obtain the course code from the course instructor or teaching assistant and enter it during registration. This will enable the instructor to access competition results for course evaluation purposes.
4. Before registration, each participant please complete the "VeriPromiseESG 2026: Pre-test Survey"; after the competition, each participant please complete the "VeriPromiseESG 2026: Post-test Survey".

For inquiries, please contact: yyteng@mail.ntpu.edu.tw

Prize

(1) Student Division Ranking Award

The top 30 teams in this competition are expected to be winners. After review and approval by the organizing committee, awards will be presented according to the following rankings:

* Note 1: The top 30 teams and the top 25% of the Private Leaderboard (regardless of their status, including members of the public) will receive an additional electronic certificate from the Ministry of Education's Artificial Intelligence Competition Program Office after submitting a report as required and having it reviewed and approved by the organizing committee's judging panel.

* Note 2: The final number of awards may be adjusted based on the number of entries and their scores. If any entry fails to meet the required standard (scores below the baseline set by the judging panel), the number of awards may be reduced or increased depending on the number of entries.

(2) Other Award Claim Guidelines

All winning teams agree to assist the organizers with the following arrangements; otherwise, they will be disqualified from receiving the award.

1. Ranking Method
• All participating teams (including students and members of the public) will be ranked uniformly based on their final scores. Only student participants are eligible to receive cash prizes. Prize money for winning teams in the public category will be awarded to the next eligible student team in the rankings.
• In the event of a replacement team, the replacement team will share the same ranking as the original team.
• Final scores will be calculated according to the competition's scoring method, and will be determined based on the results of the Private Leaderboard and report review.
2. Eligibility and Decision-Making Principles
   All winning teams agree to assist the organizers with the following arrangements; otherwise, they will be disqualified from receiving the prize:
   • Prize money will be disbursed via New Taiwan Dollar (NTD) remittance. Winning teams that meet the registration requirements and are eligible to receive the prize money must appoint a team member with a local NTD account to receive the prize money on their behalf. This team member will be the Republic of China tax filer and will be responsible for paying the relevant income tax. All relevant documents, including tax, personal data usage, and receipt documents, must be signed as required.
   • If any member of a team that wins the "Student Ranking Award" has achieved a top-three ranking (including first to third place, or gold/silver/bronze medals) three or more times in the "Ministry of Education National College Artificial Intelligence Competition (AI CUP)" organized by the "Ministry of Education Artificial Intelligence Competition and Annotation Data Collection Project Office," and then wins again in the competition, that team will only receive a certificate from the Ministry of Education, and the prize money will be awarded to the next-ranked team. The two teams will be tied for the same ranking. This rule is not retroactive, and the number of awards is calculated from the Fall 2022 competition.