Not All Subjectivity Is the Same! Defining Desiderata for the Evaluation of Subjectivity in NLP
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912988595748864 |
|---|---|
| author | Khurana, Urja van der Meer, Michiel Liscio, Enrico Fokkens, Antske Murukannaiah, Pradeep K. |
| author_facet | Khurana, Urja van der Meer, Michiel Liscio, Enrico Fokkens, Antske Murukannaiah, Pradeep K. |
| contents | Subjective judgments are part of several NLP datasets and recent work is increasingly prioritizing models whose outputs reflect this diversity of perspectives. Such responses allow us to shed light on minority voices, which are frequently marginalized or obscured by dominant perspectives. It remains a question whether our evaluation practices align with these models' objectives. This position paper proposes seven evaluation desiderata for subjectivity-sensitive models, rooted in how subjectivity is represented in NLP data and models. The desiderata are constructed in a top-down approach, keeping in mind the user-centric impact of such models. We scan the experimental setup of 60 papers and show that various aspects of subjectivity are still understudied: the distinction between ambiguous and polyphonic input, whether subjectivity is effectively expressed to the user, and a lack of interplay between different desiderata, amongst other gaps. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_28351 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Not All Subjectivity Is the Same! Defining Desiderata for the Evaluation of Subjectivity in NLP Khurana, Urja van der Meer, Michiel Liscio, Enrico Fokkens, Antske Murukannaiah, Pradeep K. Computation and Language Subjective judgments are part of several NLP datasets and recent work is increasingly prioritizing models whose outputs reflect this diversity of perspectives. Such responses allow us to shed light on minority voices, which are frequently marginalized or obscured by dominant perspectives. It remains a question whether our evaluation practices align with these models' objectives. This position paper proposes seven evaluation desiderata for subjectivity-sensitive models, rooted in how subjectivity is represented in NLP data and models. The desiderata are constructed in a top-down approach, keeping in mind the user-centric impact of such models. We scan the experimental setup of 60 papers and show that various aspects of subjectivity are still understudied: the distinction between ambiguous and polyphonic input, whether subjectivity is effectively expressed to the user, and a lack of interplay between different desiderata, amongst other gaps. |
| title | Not All Subjectivity Is the Same! Defining Desiderata for the Evaluation of Subjectivity in NLP |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2603.28351 |