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 …
algorithms on media practices has grown. We must always consider the interdisciplinary …
UTDRM: unsupervised method for training debunked-narrative retrieval models
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 …
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
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 …
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
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 …
credibility of online social media content is of tremendous importance. Credibility …
Multilingual previously fact-checked claim retrieval
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 …
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
Pioneer researches recognize evidences as crucial elements in fake news detection apart
from patterns. Existing evidence-aware methods either require laborious pre-processing …
from patterns. Existing evidence-aware methods either require laborious pre-processing …