Missing counter-evidence renders NLP fact-checking unrealistic for misinformation

M Glockner, Y Hou, I Gurevych - ar** Review and Reflection
L Kavtaradze - Digital Journalism, 2024 - Taylor & Francis
As artificial intelligence (AI) has become pervasive in journalistic production, the influence of
algorithms on media practices has grown. We must always consider the interdisciplinary …

UTDRM: unsupervised method for training debunked-narrative retrieval models

I Singh, C Scarton, K Bontcheva - EPJ Data Science, 2023 - epjds.epj.org
A key task in the fact-checking workflow is to establish whether the claim under investigation
has already been debunked or fact-checked before. This is essentially a retrieval task where …

Finding already debunked narratives via multistage retrieval: Enabling cross-lingual, cross-dataset and zero-shot learning

I Singh, C Scarton, X Song, K Bontcheva - arxiv preprint arxiv:2308.05680, 2023 - arxiv.org
The task of retrieving already debunked narratives aims to detect stories that have already
been fact-checked. The successful detection of claims that have already been debunked not …

A Survey on Automatic Credibility Assessment of Textual Credibility Signals in the Era of Large Language Models

I Srba, O Razuvayevskaya, JA Leite, R Moro… - arxiv preprint arxiv …, 2024 - arxiv.org
In the current era of social media and generative AI, an ability to automatically assess the
credibility of online social media content is of tremendous importance. Credibility …

Multilingual previously fact-checked claim retrieval

M Pikuliak, I Srba, R Moro, T Hromadka… - arxiv preprint arxiv …, 2023 - arxiv.org
Fact-checkers are often hampered by the sheer amount of online content that needs to be
fact-checked. NLP can help them by retrieving already existing fact-checks relevant to the …

Search, Examine and Early-Termination: Fake News Detection with Annotation-Free Evidences

Y Yang, Y Zhou, Q Ying, Z Qian, X Zhang - arxiv preprint arxiv …, 2024 - arxiv.org
Pioneer researches recognize evidences as crucial elements in fake news detection apart
from patterns. Existing evidence-aware methods either require laborious pre-processing …