Goodtriever: Adaptive Toxicity Mitigation with Retrieval-augmented Models

Luiza Amador Pozzobon, Beyza Ermis, Patrick Lewis, Sara Hooker

Submission Type: Regular Long Paper

Submission Track: Natural Language Generation

Submission Track 2: Human-Centered NLP

Keywords: toxicity mitigation, retrieval-augmented, continual learning

TL;DR: This work introduces a flexible methodology for mitigating toxicity in LMs that considers the evolving nature of language, achieves SOTA performance, reduces latency and improves computational efficiency.

Abstract: Considerable effort has been dedicated to mitigating toxicity, but existing methods often require drastic modifications to model parameters or the use of computationally intensive auxiliary models. Furthermore, previous approaches have often neglected the crucial factor of language's evolving nature over time. In this work, we present a comprehensive perspective on toxicity mitigation that takes into account its changing nature. We introduce Goodtriever, a flexible methodology that matches the current state-of-the-art toxicity mitigation while achieving 43% relative latency reduction during inference and being more computationally efficient. By incorporating a retrieval-based approach at decoding time, Goodtriever enables toxicity-controlled text generation. Our research advocates for an increased focus on adaptable mitigation techniques, which better reflect the data drift models face when deployed in the wild.

Submission Number: 3613