PledgeTracker is a system to monitor the fulfilment of political pledges. As part of this study, we will collect your inputs to help evaluate and improve the system. We may also collect your feedback if you submit it via the feedback form. No personal information will be collected, and all data will be anonymised and stored securely. By using the system, you agree to participate in this study under these conditions.
Please contact Andreas Vlachos and Yulong Chen if you have any concerns.
PledgeTracker is a research prototype developed to support the monitoring of political pledge fulfilment. This demo is developed by researchers at the University of Cambridge, Queen Mary University London, and Full Fact.
If you find PledgeTracker useful, please cite:
@inproceedings{chen-etal-2025-pledgetracker,
title = "{P}ledge{T}racker: A System for Monitoring the Fulfilment of Pledges",
author = "Chen, Yulong and
Schlichtkrull, Michael Sejr and
Deng, Zhenyun and
Corney, David and
Asl, Nasim and
Salisbury, Joshua and
Dudfield, Andrew and
Vlachos, Andreas",
editor = {Habernal, Ivan and
Schulam, Peter and
Tiedemann, J{\"o}rg},
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-demos.64/",
doi = "10.18653/v1/2025.emnlp-demos.64",
pages = "839--850",
ISBN = "979-8-89176-334-0",
abstract = "Political pledges reflect candidates' policy commitments, but tracking their fulfilment requires reasoning over incremental evidence distributed across multiple, dynamically updated sources. Existing methods simplify this task into a document classification task, overlooking its dynamic temporal and multi-document nature. To address this issue, we introduce PledgeTracker, a system that reformulates pledge verification into structured event timeline construction. PledgeTracker consists of three core components: (1) a multi-step evidence retrieval module; (2) a timeline construction module and; (3) a fulfilment filtering module, allowing the capture of the evolving nature of pledge fulfilment and producing interpretable and structured timelines. We evaluate PledgeTracker in collaboration with professional fact-checkers in real-world workflows, demonstrating its effectiveness in retrieving relevant evidence and reducing human verification effort."
}