Large-scale language models, like ChatGPT, have garnered significant media attention and
stunned the public with their remarkable capacity for generating coherent text from short …

Abstract Language models, such as BART and GPT, have been shown to be highly effective
at producing quality headlines. However, without clear guidelines for what constitutes a …

This paper describes the results of the Knowledge Graph Question Answering (KGQA)
shared task that was co-located with the TextGraphs 2024 workshop. In this task, given a …

Aiming at mining high quality topics by accumulating and utilizing semantic knowledge for a
stream of documents, lifelong topic modeling (LTM) has attracted more and more attentions …

Text style transfer techniques are gaining popularity in natural language processing
allowing paraphrasing text in the required form: from toxic to neural, from formal to informal …

Text generation has become more accessible than ever, and the increasing interest in these
systems, especially those using large language models, has spurred an increasing number …

Authorship style transfer aims to rewrite a given text into a specified target while preserving
the original meaning in the source. Existing approaches rely on the availability of a large …

While state-of-the-art language models excel at the style transfer task, current work does not
address explainability of style transfer systems. Explanations could be generated using …

Text detoxification is the task of transferring the style of text from toxic to neutral. While here
are approaches yielding promising results in monolingual setup, eg,(Dale et al., 2021; …

In this paper, we present our novel systems developed for the SemEval-2024 hallucination
detection task. Our investigation spans a range of strategies to compare model predictions …