PledgeTracker: A System for Monitoring the Fulfilment of Pledges

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Chen, Yulong, Schlichtkrull, Michael Sejr, Deng, Zhenyun, Corney, David, Asl, Nasim, Salisbury, Joshua, Dudfield, Andrew, Vlachos, Andreas
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912587607703552
author Chen, Yulong
Schlichtkrull, Michael Sejr
Deng, Zhenyun
Corney, David
Asl, Nasim
Salisbury, Joshua
Dudfield, Andrew
Vlachos, Andreas
author_facet Chen, Yulong
Schlichtkrull, Michael Sejr
Deng, Zhenyun
Corney, David
Asl, Nasim
Salisbury, Joshua
Dudfield, Andrew
Vlachos, Andreas
contents 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 \textsc{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.
format Preprint
id arxiv_https___arxiv_org_abs_2509_11804
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PledgeTracker: A System for Monitoring the Fulfilment of Pledges
Chen, Yulong
Schlichtkrull, Michael Sejr
Deng, Zhenyun
Corney, David
Asl, Nasim
Salisbury, Joshua
Dudfield, Andrew
Vlachos, Andreas
Computation and Language
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 \textsc{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.
title PledgeTracker: A System for Monitoring the Fulfilment of Pledges
topic Computation and Language
url https://arxiv.org/abs/2509.11804