A Survey on Fairness in Large Language Models

arXiv:2308.10149v2 Announce Type: replace
Abstract: Large Language Models (LLMs) have shown powerful performance and development prospects and are widely deployed in the real world. However, LLMs can capture social biases from unprocessed training data and propagate the biases to downstream tasks. Unfair LLM systems have undesirable social impacts and potential harms. In this paper, we provide a comprehensive review of related research on fairness in LLMs. Considering the influence of parameter magnitude and training paradigm on research strategy, we divide …

abstract arxiv biases cs.ai cs.cl data development fairness impacts language language models large language large language models llm llms performance prospects social survey systems tasks training training data type world