Does Writing with Language Models Reduce Content Diversity?

arXiv:2309.05196v2 Announce Type: replace-cross
Abstract: Large language models (LLMs) have led to a surge in collaborative writing with model assistance. As different users incorporate suggestions from the same model, there is a risk of decreased diversity in the produced content, potentially limiting diverse perspectives in public discourse. In this work, we measure the impact of co-writing on diversity via a controlled experiment, where users write argumentative essays in three setups -- using a base LLM (GPT3), a feedback-tuned LLM (InstructGPT), …

abstract arxiv collaborative cs.cl cs.cy cs.hc cs.lg discourse diverse diversity language language models large language large language models llms perspectives public reduce risk suggestions type work writing