Publication details

B. Muscato, P. Bushipaka, G. Gezici, L. Passaro, F. Giannotti and T. Cucinotta. "Embracing Diversity: A Multi-Perspective Approach with Soft Labels," 4th Internatinoal Conference on Hybrid Human-Artificial Intelligence (HHAI 2025), June 9-13, 2025, Pisa, Italy.

Abstract

Prior studies show that adopting the annotation diversity shaped by different backgrounds and life experiences and incorporating them into the model learning, i.e. multi-perspective approach, contribute to the development of more responsible models. Thus, in this paper we propose a new framework for designing and further evaluating perspective-aware models on stance detection task, in which multiple annotators assign stances based on a controversial topic. We also share a new dataset established through obtaining both human and LLM annotations. Results show that the multi-perspective approach yields better classification performance (higher F1-scores), outperforming the traditional approaches that use a single ground-truth, while displaying lower model confidence scores, probably due to the high level of subjectivity of the stance detection task.

See paper on publisher's website

Download paper

DOI: 10.3233/FAIA250654

BibTeX entry:

@inbook{Muscato_2025,
     title={Embracing Diversity: A Multi-Perspective Approach with Soft Labels},
     ISBN={9781643686110},
     ISSN={1879-8314},
     url={http://dx.doi.org/10.3233/FAIA250654},
     DOI={10.3233/faia250654},
     booktitle={HHAI 2025},
     publisher={IOS Press},
     author={Muscato, Benedetta and Bushipaka, Praveen and Gezici, Gizem and Passaro, Lucia and Giannotti, Fosca and Cucinotta, Tommaso},
     year={2025},
     month=sep }

Last updated on
14 November 2025