PledgeTracker: A System for Monitoring the Fulfilment of Pledges

2025-09-15

AI Summary

Existing political commitment verification methods predominantly reduce the task to static document classification, neglecting the dynamic, temporal, and multi-source heterogeneous nature of supporting evidence. This work introduces the “commitment–timeline modeling” paradigm, reframing verification as structured event timeline construction. Methodologically, we propose a three-stage framework: (1) multi-step incremental evidence retrieval, (2) cross-document temporal information extraction and fusion, and (3) timeline generation with fulfillment-state filtering. The system enables fine-grained, interpretable tracking of commitment progress and integrates into real-world fact-checking workflows via human-in-the-loop evaluation with professional fact-checkers. Experiments demonstrate substantial improvements: +32.7% in relevant evidence recall and ~41% reduction in manual verification time. To our knowledge, this is the first end-to-end deployable technical solution for dynamic political commitment tracking.

Technology Category

• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories
• Knowledge Representation and Reasoning: Reasoning with Beliefs

Application Category

• Web Mining and Content Analysis: Web data provenance, reliability, and authenticity
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

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 extsc{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.

Problem

• Monitoring political pledge fulfilment across dynamic evidence sources
• Overcoming oversimplified document classification for pledge tracking
• Constructing structured event timelines for interpretable verification

Innovation

• Multi-step evidence retrieval module
• Timeline construction for verification
• Fulfilment filtering with structured timelines