"One-Size-Fits-All"? Examining Expectations around What Constitute "Fair" or "Good" NLG System Behaviors

TL;DR

This paper investigates societal expectations for fair and appropriate behaviors of NLG systems across different social groups, highlighting tensions between invariance and adaptation through five case studies.

Contribution

It provides empirical insights into the conflicting motivations behind invariance and adaptation in NLG fairness, revealing key challenges and considerations.

Findings

Motivations for adaptation include social norms and cultural differences.

Motivations for invariance include prescriptivism and technical challenges.

Identifies open challenges in defining fair NLG behaviors.

Abstract

Fairness-related assumptions about what constitute appropriate NLG system behaviors range from invariance, where systems are expected to behave identically for social groups, to adaptation, where behaviors should instead vary across them. To illuminate tensions around invariance and adaptation, we conduct five case studies, in which we perturb different types of identity-related language features (names, roles, locations, dialect, and style) in NLG system inputs. Through these cases studies, we examine people's expectations of system behaviors, and surface potential caveats of these contrasting yet commonly held assumptions. We find that motivations for adaptation include social norms, cultural differences, feature-specific information, and accommodation; in contrast, motivations for invariance include perspectives that favor prescriptivism, view adaptation as unnecessary or too difficult for NLG systems to do appropriately, and are wary of false assumptions. Our findings highlight open challenges around what constitute "fair" or "good" NLG system behaviors.