English

Learning from Red Teaming: Gender Bias Provocation and Mitigation in Large Language Models

Computation and Language 2023-10-18 v1 Artificial Intelligence

Abstract

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.

Keywords

Cite

@article{arxiv.2310.11079,
  title  = {Learning from Red Teaming: Gender Bias Provocation and Mitigation in Large Language Models},
  author = {Hsuan Su and Cheng-Chu Cheng and Hua Farn and Shachi H Kumar and Saurav Sahay and Shang-Tse Chen and Hung-yi Lee},
  journal= {arXiv preprint arXiv:2310.11079},
  year   = {2023}
}
R2 v1 2026-06-28T12:53:03.270Z