Optimizing Token Usage on Large Language Model Conversations Using the Design Structure Matrix

TL;DR

This paper introduces a novel approach using the Design Structure Matrix to optimize token usage in large language model conversations, reducing costs and improving efficiency by organizing dialogue and managing context windows effectively.

Contribution

It applies the Design Structure Matrix from engineering to LLM conversation management, offering a new methodology for token optimization and context organization.

Findings

DSM effectively organizes conversations to minimize token usage

Clustering and sequencing improve context window management

Method reduces token costs in LLM interactions

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.