LMStyle Benchmark: Evaluating Text Style Transfer for Chatbots

arXiv:2403.08943v1 Announce Type: new
Abstract: Since the breakthrough of ChatGPT, large language models (LLMs) have garnered significant attention in the research community. With the development of LLMs, the question of text style transfer for conversational models has emerged as a natural extension, where chatbots may possess their own styles or even characters. However, standard evaluation metrics have not yet been established for this new settings. This paper aims to address this issue by proposing the LMStyle Benchmark, a novel evaluation …

abstract arxiv attention benchmark characters chatbots chatgpt community conversational cs.cl development extension language language models large language large language models llms natural question research research community style style transfer text text style transfer transfer type