Optimizing Token Usage on Large Language Model Conversations Using the Design Structure Matrix
DS 134: Proceedings of the 26th International DSM Conference (DSM 2024), Stuttgart, Germany
Year: 2024
Editor: Harold (Mike) Stowe; Christopher Langner; Matthias Kreimeyer; Tyson R. Browning; Steven D. Eppinger; Ali A. Yassine
Author: Ramon Maria Garcia Alarcia; Alessandro Golkar
Series: DSM
Institution: Technical University of Munich, Germany
Page(s): 069-078
DOI number: 10.35199/dsm2024.08
Abstract
As Large Language Models become ubiquitous in many sectors and tasks, there is a need to reduce token usage, overcoming challenges such as short context windows, limited output sizes, and costs associated with token intake and generation, especially in API-served LLMs. This work brings the Design Structure Matrix from the engineering design discipline into LLM conversation optimization. Applied to a use case in which the LLM conversation is about the design of a spacecraft and its subsystems, the DSM, with its analysis tools such as clustering and sequencing, demonstrates being an effective tool to organize the conversation, minimizing the number of tokens sent to or retrieved from the LLM at once, as well as grouping chunks that can be allocated to different context windows. Hence, this work broadens the current set of methodologies for token usage optimization and opens new avenues for the integration of engineering design practices into LLMs.
Keywords: Large Language Models, token usage optimization, context window, output tokens, Design Structure Matrix