Recourse for reclamation: Chatting with generative language models
This addresses the issue of rigid moderation in generative language models for users, especially marginalized communities, though it is incremental as it builds on existing algorithmic recourse concepts.
The paper tackles the problem of toxicity scoring in generative language models limiting access to information and cultural expression, particularly for marginalized groups, by introducing a recourse mechanism that allows users to dynamically set toxicity thresholds, with a pilot study (n=30) showing improved usability compared to fixed-threshold filtering.
Researchers and developers increasingly rely on toxicity scoring to moderate generative language model outputs, in settings such as customer service, information retrieval, and content generation. However, toxicity scoring may render pertinent information inaccessible, rigidify or "value-lock" cultural norms, and prevent language reclamation processes, particularly for marginalized people. In this work, we extend the concept of algorithmic recourse to generative language models: we provide users a novel mechanism to achieve their desired prediction by dynamically setting thresholds for toxicity filtering. Users thereby exercise increased agency relative to interactions with the baseline system. A pilot study ($n = 30$) supports the potential of our proposed recourse mechanism, indicating improvements in usability compared to fixed-threshold toxicity-filtering of model outputs. Future work should explore the intersection of toxicity scoring, model controllability, user agency, and language reclamation processes -- particularly with regard to the bias that many communities encounter when interacting with generative language models.