Sequential Decision-Making for Inline Text Autocomplete

arXiv:2403.15502v1 Announce Type: cross
Abstract: Autocomplete suggestions are fundamental to modern text entry systems, with applications in domains such as messaging and email composition. Typically, autocomplete suggestions are generated from a language model with a confidence threshold. However, this threshold does not directly take into account the cognitive load imposed on the user by surfacing suggestions, such as the effort to switch contexts from typing to reading the suggestion, and the time to decide whether to accept the suggestion. In …

abstract applications arxiv autocomplete cognitive confidence cs.cl cs.hc cs.lg decision domains email generated however language language model making messaging modern suggestions systems text text autocomplete threshold type