Understanding the Promise and Limits of Automated Fact-Checking

By Lucas Graves. 2018

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Evaluation & Benchmarks

Citations in the corpus

ProoFVer: Natural Logic Theorem Proving for Fact Verification (2021, background): “For a task like fact verification, with sensitive areas of application (Graves, 2018), explaining the reasoning behind the decision making process is valuable.”
Generating Fact Checking Briefs (2020, positive): “However, due to the limitations of existing automated solutions, practitioners prefer solutions that improve efﬁciency in reaching a verdict, instead of approaches to the complete process (Graves, 2018).”
Automated Fact Checking: Task Formulations, Methods and Future Directions (2018, background): “The increased demand for fact checking has stimulated a rapid progress in developing tools and systems to automate the task, or parts thereof (Babakar and Moy, 2016; Graves, 2018).”
User Perceptions and Trust of Explainable Machine Learning Fake News Detectors (2022, background): “This automatic detection of fake news can help prevent false information from going viral on social media and assist journalists and fact-checkers in responding more effectively to misinformation (Graves, 2018).”
A Survey on Automated Fact-Checking (2021, methodology): “More broadly it would be dangerous to make such strong claims about the world given the well-known limitations (Graves, 2018).”
FEVEROUS: Fact Extraction and VERification Over Unstructured and Structured information (2021, methodology): “Interest in automating fact veriﬁcation has been growing as the volume of potentially misleading and false claims rises [Graves, 2018], resulting in the development of both fully automated methods (see Thorne and Vlachos [2018], Zubiaga et al. [2018], Hardalov et al. [2021] for recent surveys) as…”
Explainable Automated Fact-Checking: A Survey (2020, background): “Graves (2018) states that fact-checking has three parts: identiﬁcation , veriﬁcation , and correction .”
Synthetic Lies: Understanding AI-Generated Misinformation and Evaluating Algorithmic and Human Solutions (2023, background): “However, it remains unclear as to what extent fact-checking, whether by humans or assisted by algorithms, is agile and adaptable to the rapidly evolving misinformation ecosystem [38].”