Locating and Mitigating Gender Bias in Large Language Models

arXiv:2403.14409v1 Announce Type: new
Abstract: Large language models(LLM) are pre-trained on extensive corpora to learn facts and human cognition which contain human preferences. However, this process can inadvertently lead to these models acquiring biases and stereotypes prevalent in society. Prior research has typically tackled the issue of bias through a one-dimensional perspective, concentrating either on locating or mitigating it. This limited perspective has created obstacles in facilitating research on bias to synergistically complement and progressively build upon one another. In …

abstract arxiv bias biases cognition cs.ai cs.cl facts gender gender bias however human issue language language models large language large language models learn llm prior process research society stereotypes through type