The economic trade-offs of large language models: A case study
It addresses cost-benefit trade-offs for companies using LLMs in customer service, but the findings are incremental as they are based on a limited case study.
This paper assesses the practical cost and impact of large language models (LLMs) for enterprise customer service, finding that the usability of model responses can offset significant inference cost differences in a case study with a single brand.
Contacting customer service via chat is a common practice. Because employing customer service agents is expensive, many companies are turning to NLP that assists human agents by auto-generating responses that can be used directly or with modifications. Large Language Models (LLMs) are a natural fit for this use case; however, their efficacy must be balanced with the cost of training and serving them. This paper assesses the practical cost and impact of LLMs for the enterprise as a function of the usefulness of the responses that they generate. We present a cost framework for evaluating an NLP model's utility for this use case and apply it to a single brand as a case study in the context of an existing agent assistance product. We compare three strategies for specializing an LLM - prompt engineering, fine-tuning, and knowledge distillation - using feedback from the brand's customer service agents. We find that the usability of a model's responses can make up for a large difference in inference cost for our case study brand, and we extrapolate our findings to the broader enterprise space.