5 papers · 1 filter
NumPert: Numerical Perturbations to Probe Language Models for Veracity Prediction
Peter Røysland Aarnes, Vinay Setty
Large language models show strong performance on knowledge intensive tasks such as fact-checking and question answering, yet they often struggle with numerical reasoning. We presen…
IAI Group at CheckThat! 2024: Transformer Models and Data Augmentation for Checkworthy Claim Detection
Peter Røysland Aarnes, Vinay Setty, Petra GaluÅ¡Äáková
This paper describes IAI group's participation for automated check-worthiness estimation for claims, within the framework of the 2024 CheckThat! Lab "Task 1: Check-Worthiness Estim…
QuestGen: Effectiveness of Question Generation Methods for Fact-Checking Applications
Ritvik Setty, Vinay Setty
Verifying fact-checking claims poses a significant challenge, even for humans. Recent approaches have demonstrated that decomposing claims into relevant questions to gather evidenc…
FactCheck Editor: Multilingual Text Editor with End-to-End fact-checking
Vinay Setty
We introduce 'FactCheck Editor', an advanced text editor designed to automate fact-checking and correct factual inaccuracies. Given the widespread issue of misinformation, often a…
Surprising Efficacy of Fine-Tuned Transformers for Fact-Checking over Larger Language Models
Vinay Setty
In this paper, we explore the challenges associated with establishing an end-to-end fact-checking pipeline in a real-world context, covering over 90 languages. Our real-world exper…