Not All Subjectivity Is the Same! Defining Desiderata for the Evaluation of Subjectivity in NLP

TL;DR

This paper proposes seven evaluation criteria for subjectivity in NLP models, emphasizing user impact and highlighting gaps in current research on diverse perspectives.

Contribution

It introduces a set of desiderata for evaluating subjectivity-sensitive NLP models and analyzes existing research to identify key gaps.

Findings

Various aspects of subjectivity are understudied in NLP.

Current evaluations often lack focus on ambiguous and polyphonic input.

There are gaps in how subjectivity is effectively communicated to users.

Abstract

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.