{"type":"ScholarlyArticle","title":"Perspectives in Play: A Multi-Perspective Approach for More Inclusive NLP Systems","authors":[{"name":"Benedetta Muscato","slug":"benedetta-muscato","given":"Benedetta","family":"Muscato","affiliation":""},{"name":"Lucia Passaro","slug":"lucia-passaro","given":"Lucia","family":"Passaro","affiliation":""},{"name":"Gizem Gezici","slug":"gizem-gezici","given":"Gizem","family":"Gezici","affiliation":""},{"name":"Fosca Giannotti","slug":"fosca-giannotti","given":"Fosca","family":"Giannotti","affiliation":""}],"abstract":"In the realm of Natural Language Processing (NLP), common approaches for handling human disagreement consist of aggregating annotators' viewpoints to establish a single ground truth. However, prior studies show that disregarding individual opinions can lead to the side-effect of under-representing minority perspectives, especially in subjective tasks, where annotators may systematically disagree because of their preferences. Recognizing that labels reflect the diverse backgrounds, life experiences, and values of individuals, this study proposes a new multi-perspective approach using soft labels to encourage the development of the next generation of perspective-aware models—more  inclusive and pluralistic. We conduct an extensive analysis across diverse subjective text classification tasks including hate speech, irony, abusive language, and stance detection, to highlight the importance of capturing human disagreements, often overlooked by traditional aggregation methods. Results show that the multi-perspective approach not only better approximates human label distributions, as measured by Jensen-Shannon Divergence (JSD), but also achieves superior classification performance (higher F1-scores), outperforming traditional approaches. However, our approach exhibits lower confidence in tasks like irony and stance detection, likely due to the inherent subjectivity present in the texts. Lastly, leveraging Explainable AI (XAI), we explore model uncertainty and uncover meaningful insights into model predictions. All implementation details are available at our github repo.","doi":"10.24963/ijcai.2025/1092","url":"https://ijcai.org/proceedings/2025/1092","pdf":"https://ijcai.org/proceedings/2025/1092.pdf","markdown":"https://ijcai.org/proceedings/2025/1092.md","bibtex":"https://ijcai.org/proceedings/2025/bibtex/1092","volume":{"slug":"2025","title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2025","url":"https://ijcai.org/proceedings/2025/","year":2025,"location":"Montreal, Canada","dates":"16-22 August 2025","editors":"James Kwok","isbn":"978-1-956792-06-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2025"},"section":"AI and Social Good","track":"AI and Social Good","number":1092,"pages":{"first":9827,"last":9835},"keywords":["Natural Language Processing: General","Uncertainty in AI: General","AI Ethics, Trust, Fairness: General","Humans and AI: General"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}