Learning from Red Teaming: Gender Bias Provocation and Mitigation in Large Language Models
This addresses bias issues in AI chatbots, which can harm users, but the approach is incremental as it builds on existing red teaming and in-context learning techniques.
The paper tackles the problem of gender bias in large language models by proposing an automated method to generate test cases for detection and using them for mitigation via in-context learning, resulting in fairer responses from the models.
Recently, researchers have made considerable improvements in dialogue systems with the progress of large language models (LLMs) such as ChatGPT and GPT-4. These LLM-based chatbots encode the potential biases while retaining disparities that can harm humans during interactions. The traditional biases investigation methods often rely on human-written test cases. However, these test cases are usually expensive and limited. In this work, we propose a first-of-its-kind method that automatically generates test cases to detect LLMs' potential gender bias. We apply our method to three well-known LLMs and find that the generated test cases effectively identify the presence of biases. To address the biases identified, we propose a mitigation strategy that uses the generated test cases as demonstrations for in-context learning to circumvent the need for parameter fine-tuning. The experimental results show that LLMs generate fairer responses with the proposed approach.