The lack of high-quality training data remains a significant challenge in NLP. Manual
annotation methods, such as crowdsourcing, are costly, require intricate task design skills …

The growing use of digital media or social media has given a platform to the people to
deliver their ideas and viewpoints openly. It is facilitating the rapid spread of contrasting …

The rapid development of autoregressive Large Language Models (LLMs) has significantly
improved the quality of generated texts, necessitating reliable machine-generated text …

This paper provides an overview of our contributions to the PAN at CLEF2024 Oppositional
thinking analysis shared task, which focuses on distinguishing between conspiratorial and …

The COVID-19 pandemic sparked a new age of conspiracy theories in society. This has
become an issue, especially since these theories are mixed in with reasonable arguments …

Conspiracy theories [1] are complex narratives that attempt to explain the ultimate causes of
significant events as cover plots orchestrated by secret, powerful, and malicious groups …

Abstract 2024 marks the 25 th birthday for CLEF, an evaluation campaign activity which has
applied the Cranfield evaluation paradigm to the testing of multilingual and multimodal …

The shared task of PAN 2024 addresses the need to distinguish between critical and
conspiratorial texts in relation to public health measures during the COVID-19 pandemic. In …

This paper investigates the detection of conspiracy-related messages on Telegram within
the PAN 2024 task on oppositional thinking analysis. The proposed approach aims to …

Team IUCL used a fine-tuned DeBERTa [1] with a sequence classification head as its basis.
DeBERTa was finetuned on an augmented dataset comprising the PAN24 [2] training set …