GTA: Gated Toxicity Avoidance for LM Performance Preservation
This addresses the issue of balancing toxicity avoidance with model performance for users of generative language models, though it appears incremental as it builds on existing CTG methods.
The paper tackles the problem of existing Controllable Text Generation methods reducing toxicity but also harming language model performance, and introduces Gated Toxicity Avoidance (GTA) to achieve comparable toxicity reduction while preserving generation performance.
Caution: This paper includes offensive words that could potentially cause unpleasantness. The fast-paced evolution of generative language models such as GPT-4 has demonstrated outstanding results in various NLP generation tasks. However, due to the potential generation of offensive words related to race or gender, various Controllable Text Generation (CTG) methods have been proposed to mitigate the occurrence of harmful words. However, existing CTG methods not only reduce toxicity but also negatively impact several aspects of the language model's generation performance, including topic consistency, grammar, and perplexity. This paper explores the limitations of previous methods and introduces a novel solution in the form of a simple Gated Toxicity Avoidance (GTA) that can be applied to any CTG method. We also evaluate the effectiveness of the proposed GTA by comparing it with state-of-the-art CTG methods across various datasets. Our findings reveal that gated toxicity avoidance efficiently achieves comparable levels of toxicity reduction to the original CTG methods while preserving the generation performance of the language model.