2 citations · 2 across the 8 of their papers we have counts for
4 papers · 1 filter
Benchmarking Argumentative Behaviour of LLMs: A Study of Defences Against Character Attacks
Ewelina Gajewska, Katarzyna Budzynska, Jaroslaw Chudziak
Large Language Models (LLMs) are increasingly deployed as argumentative agents in persuasive dialogues, necessitating rigorous evaluation of their debating competence relative to h…
How Ethos and Pathos Appeals Resonate in Reader Interpretations of Social Media Messages
Ewelina Gajewska, Katarzyna Budzynska, Jaroslaw Chudziak +1
Rhetorical strategies and their influence on audiences are often studied through social media posts and comments. However, this focus overlooks the universal audience, which is the…
Improving Implicit Hate Speech Detection via a Community-Driven Multi-Agent Framework
Ewelina Gajewska, Katarzyna Budzynska, Jarosław A Chudziak
This work proposes a contextualised detection framework for implicitly hateful speech, implemented as a multi-agent system comprising a central Moderator Agent and dynamically cons…
Algorithmic Fairness in NLP: Persona-Infused LLMs for Human-Centric Hate Speech Detection
Ewelina Gajewska, Arda Derbent, Jaroslaw A Chudziak +1
In this paper, we investigate how personalising Large Language Models (Persona-LLMs) with annotator personas affects their sensitivity to hate speech, particularly regarding biases…