[Submitted on 28 Jul 2024]
View a PDF of the paper titled Impact of Decoding Methods on Human Alignment of Conversational LLMs, by Shaz Furniturewala and 2 other authors
Abstract: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.
Submission history
From: Shaz Furniturewala [view email]
[v1]
Sun, 28 Jul 2024 16:31:09 UTC (1,174 KB)
Source link
lol
