Explainable Automated Fact-Checking: A Survey

By Neema Kotonya, Francesca Toni. 2020

153 citations recorded by the source corpus.

A number of exciting advances have been made in automated fact-checking thanks to increasingly larger datasets and more powerful systems, leading to improvements in the complexity of claims which can be accurately fact-checked. However, despite these advances, there are still desirable functionalities missing from the fact-checking pipeline. In this survey, we focus on the explanation functionality – that is fact-checking systems providing reasons for their predictions. We summarize existing methods for explaining the predictions of fact-checking systems and we explore trends in this topic. Further, we consider what makes for good explanations in this specific domain through a comparative analysis of existing fact-checking explanations against some desirable properties. Finally, we propose further research directions for generating fact-checking explanations, and describe how these may lead to improvements in the research area.

Subfields: Artificial Intelligence, Information Systems and Management, Natural Language Processing, AI Ethics, Fairness & Society

How researchers see this paper

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

In Artificial Intelligence

In Information Systems and Management

In Natural Language Processing

In AI Ethics, Fairness & Society

Citations in the corpus

ProoFVer: Natural Logic Theorem Proving for Fact Verification (2021, background): “A possible exception here would be the rule discovery models, however, their performance often suffers due to limited knowledge base coverage and/or the noise in rule extraction from text (Kotonya and Toni, 2020a; Pezeshkpour et al., 2020).”
Automated Fact-Checking for Assisting Human Fact-Checkers (2021, background): “In the literature, there have been a number of surveys on “fake news” [Zhou and Zafarani, 2020; Cardoso Durier da Silva et al., 2019], misinformation [Islam et al., 2020], factchecking [Kotonya and Toni, 2020], truth discovery [Li et al., 2016], and propaganda detection [Martino et al., 2020].”
Teach Me to Explain: A Review of Datasets for Explainable Natural Language Processing (2021, methodology): “Datasets and methods for explaining fact checking [63] 31 and reading comprehension [114] have been reviewed; we are the first to review all datasets with 32 textual explanations regardless of task, comprehensively categorize them into three distinct classes, 33 and provide critical retrospectives a”
Policy Compliance Detection via Expression Tree Inference (2022, methodology): “To this end, we formulate this task as one of structured prediction (Kulmizev et al., 2019), i.e. we decompose policy texts into their constituent spans, rephrase these spans as questions, and use these questions to infer an expression tree.”
FEVEROUS: Fact Extraction and VERification Over Unstructured and Structured information (2021, background): “…[Popat et al., 2016, Baly et al., 2018, Augenstein et al., 2019], or bypass the retrieval challenge entirely by extracting evidence directly from the fact checking articles [Alhindi et al., 2018, Hanselowski et al., 2019, Kotonya and Toni, 2020b] or scientiﬁc literature [Wadden et al., 2020].”
When retrieval outperforms generation: Dense evidence retrieval for scalable fake news detection (2025, unknown): “RAWFC LIAR-RAW P R F1 P R F1 Traditional approach dEFEND (Shu et al., 2019) 44.90 43.20 44.00 23.00 18.50 20.50 SentHAN (Ma et al., 2019) 45.70 45.50 45.60 22.60 20.00 21.20 SBERT-FC (Kotonya and Toni, 2020a,b) 51.10 46.00 48.40 24.10 22.10 23.10 CofCED (Yang et al., 2022) 53.00 51.00 52.00 29.50 29”