[PDF][PDF] Overview of the multilingual text detoxification task at pan 2024
Despite different countries and social platform regulations, digital abusive speech persists
as a significant challenge. One of the way to tackle abusive, or more specifically, toxic …
as a significant challenge. One of the way to tackle abusive, or more specifically, toxic …
ELOQUENT CLEF shared tasks for evaluation of generative language model quality
ELOQUENT is a set of shared tasks for evaluating the quality and usefulness of generative
language models. ELOQUENT aims to bring together some high-level quality criteria …
language models. ELOQUENT aims to bring together some high-level quality criteria …
[PDF][PDF] Towards a Computational Framework for Distinguishing Critical and Conspiratorial Texts by Elaborating on the Context and Argumentation with LLMs
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 …
conspiratorial texts in relation to public health measures during the COVID-19 pandemic. In …
[PDF][PDF] Detection of Conspiracy vs. Critical Narratives and Their Elements using NLP
A Albladi, C Seals - Working Notes of CLEF, 2024 - ceur-ws.org
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 …
deliver their ideas and viewpoints openly. It is facilitating the rapid spread of contrasting …
[PDF][PDF] Marsan at PAN 2024 TextDetox: ToxiCleanse RL, Paving the Way for Toxicity-Free Online Discourse
Addressing the pervasive issue of toxicity in online communication requires innovative
solutions beyond mere identification and removal of harmful content. This paper presents …
solutions beyond mere identification and removal of harmful content. This paper presents …
[PDF][PDF] Small Language Models and Large Language Models in Oppositional thinking analysis: Capabilities and Biases and Challenges
The proliferation of misinformation and conspiracy theories needs robust methods to
differentiate legitimate critical discourse from harmful conspiratorial narratives. This study …
differentiate legitimate critical discourse from harmful conspiratorial narratives. This study …
[PDF][PDF] IUCL at PAN 2024: Using Data Augmentation for Conspiracy Theory Detection
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 …
DeBERTa was finetuned on an augmented dataset comprising the PAN24 [2] training set …
[PDF][PDF] Conspiracy vs Critical Thinking Using an Ensemble of Transformers with Data Augmentation Techniques
A Tulbure, MC Ardanuy - Working Notes of CLEF, 2024 - ceur-ws.org
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 …
thinking analysis shared task, which focuses on distinguishing between conspiratorial and …
[PDF][PDF] BLGAV: Generative AI Author Verification Model Based on BERT and BiLSTM
L Guo, W Yang, L Ma, J Ruan - Working Notes of CLEF, 2024 - ceur-ws.org
In recent years, large language models like GPT-3, BERT, and GPT-4 have made significant
advancements in the field of natural language processing, enhancing tasks such as …
advancements in the field of natural language processing, enhancing tasks such as …
[PDF][PDF] Detection of conspiracy-related messages in Telegram with anonymized named entities
J Gómez-Romero, S González-Silot… - Working Notes of …, 2024 - ceur-ws.org
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 …
the PAN 2024 task on oppositional thinking analysis. The proposed approach aims to …