5 papers
IMPACTeen: Intentions, Manipulation, Persuasion, Annotations, and Consequences in Teen Communication Dataset
Aleksander Szczęsny, Wiktoria Mieleszczenko-Kowszewicz, Maciej Markiewicz +5
IMPACTeen is a dataset of textual social influence scenarios spanning interpersonal, media-based, and digital settings in an adolescent context. It contains 1,021 texts, 5,100 indi…
Sociodemographic Biases in Educational Counselling by Large Language Models
Tomasz Adamczyk, Wiktoria Mieleszczenko-Kowszewicz, Beata Bajcar +6
As Large Language Models (LLMs) are increasingly integrated into educational settings, understanding their potential biases is critical. This study examines sociodemographic biases…
How Annotation Trains Annotators: Competence Development in Social Influence Recognition
Maciej Markiewicz, Beata Bajcar, Wiktoria Mieleszczenko-Kowszewicz +8
Human data annotation, especially when involving experts, is often treated as an objective reference. However, many annotation tasks are inherently subjective, and annotators' judg…
Unraveling SITT: Social Influence Technique Taxonomy and Detection with LLMs
Wiktoria Mieleszczenko-Kowszewicz, Beata Bajcar, Aleksander Szczęsny +4
In this work we present the Social Influence Technique Taxonomy (SITT), a comprehensive framework of 58 empirically grounded techniques organized into nine categories, designed to…
Mind What You Ask For: Emotional and Rational Faces of Persuasion by Large Language Models
Wiktoria Mieleszczenko-Kowszewicz, Beata Bajcar, Jolanta Babiak +3
Be careful what you ask for, you just might get it. This saying fits with the way large language models (LLMs) are trained, which, instead of being rewarded for correctness, are in…