To be included into chatbot systems, Large language models (LLMs) must be aligned with human conversational conventions. However, being trained mainly on web-scraped data gives existing LLMs a voice closer to informational text than actual human speech. In this paper, we examine the effect of decoding methods on the alignment between LLM-generated and human conversations, including Beam Search, Top K Sampling, and Nucleus Sampling. We present new measures of alignment in substance, style, and psychometric orientation, and experiment with two conversation datasets. Our results provide subtle insights: better alignment is attributed to fewer beams in Beam Search and lower values of P in Nucleus Sampling. We also find that task-oriented and open-ended datasets perform differently in terms of alignment, indicating the significance of taking into account the context of the interaction.
@article{arxiv.2407.19526,
title = {Impact of Decoding Methods on Human Alignment of Conversational LLMs},
author = {Shaz Furniturewala and Kokil Jaidka and Yashvardhan Sharma},
journal= {arXiv preprint arXiv:2407.19526},
year = {2024}
}