Papers with toxic degeneration
Language Model Detoxification in Dialogue with Contextualized Stance Control (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing work on Language Model detoxification has focused on reducing the toxicity of the generation itself without consideration of the context. |
| Approach: | They propose a method to do context-dependent detoxification without taking into account the stance of the generated response. |
| Outcome: | The proposed method can learn the context-dependent stance control strategies while keeping a low self-toxicity of the underlying LM. |
CFL: Causally Fair Language Models Through Token-level Attribute Controlled Generation (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to control attributes of Language Models (LMs) for text generation are not safe, as toxicity and bias goals are opposed to each other. |
| Approach: | They propose a method to control the attributes of Language Models (LMs) for the text generation task using Causal Average Treatment Effect (ATE) scores and counterfactual augmentation. |
| Outcome: | The proposed architecture achieves state of the art performance for toxic degeneration, which are computed using Real Toxicity Prompts. |