AXOLOTL: Fairness through Assisted Self-Debiasing of Large Language Model Outputs
This addresses fairness issues in LLM applications for users and developers, offering a practical, low-resource solution, though it is incremental as it builds on existing debiasing strategies.
The paper tackles the problem of biases in pre-trained Large Language Models (LLMs) leading to unfair outcomes by introducing AXOLOTL, a post-processing framework that uses a zero-shot-like process to guide models to self-debias outputs, minimizing computational costs and preserving performance.
Pre-trained Large Language Models (LLMs) have significantly advanced natural language processing capabilities but are susceptible to biases present in their training data, leading to unfair outcomes in various applications. While numerous strategies have been proposed to mitigate bias, they often require extensive computational resources and may compromise model performance. In this work, we introduce AXOLOTL, a novel post-processing framework, which operates agnostically across tasks and models, leveraging public APIs to interact with LLMs without direct access to internal parameters. Through a three-step process resembling zero-shot learning, AXOLOTL identifies biases, proposes resolutions, and guides the model to self-debias its outputs. This approach minimizes computational costs and preserves model performance, making AXOLOTL a promising tool for debiasing LLM outputs with broad applicability and ease of use.