[Industry] Distilled Language Models are economically efficient for the enterprise. ...mostly.
Kristen Howell, Gwen Christian, Pavel Fomitchov, Gitit Kehat, Julianne Marzulla, Leanne Rolston, Jadin Tredup, Ilana Zimmerman, Ethan Selfridge, Joseph Bradley
Industry: Industry Industry Paper
Session 5: Industry (Poster)
Conference Room: Frontenac Ballroom and Queen's Quay
Conference Time: July 11, 16:15-17:45 (EDT) (America/Toronto)
Global Time: July 11, Session 5 (20:15-21:45 UTC)
TLDR:
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. With their ability to handle large context wind...
You can open the
#paper-I66
channel in a separate window.
Abstract:
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. With their ability to handle large context windows, 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.