Argo: Efficient Importance Labeling for Enterprise Email Systems

TL;DR

Argo is a cost-efficient enterprise email labeling framework that leverages alternative schemes to large language models, achieving near GPT-4 quality at a fraction of the cost and enabling scalable, context-aware labeling.

Contribution

We introduce Argo, a novel framework that efficiently searches for cost-quality trade-offs and scales dynamically, significantly reducing inference and profiling costs for enterprise email labeling.

Findings

Achieves 148-167X inference cost reduction with negligible quality loss.

Reduces profiling costs by 20-640000X across datasets.

Enables large-scale, context-aware email labeling for enterprises.

Abstract

Email importance labeling has long been a critical yet challenging problem for businesses and individuals. Traditional approaches; such as keyword matching, user-defined rules, and sender-based heuristics; demand extensive manual feature engineering and fail to scale effectively or generalize. Recent advances in large language models (LLMs) demonstrate strong potential and a natural fit for this task, offering deep contextual understanding and superior labeling quality. However, using LLM models like GPT-4.1 at enterprise email volumes incurs prohibitive computational costs and hinders real-world deployment. We explore the trade-off space of using alternative labeling schemes as opposed to GPT4.1 scale LLMs, with the goal of achieving near GPT level labeling quality with significantly lower cost. We develop Argo, an enterprise email labeling framework, where we construct a profiler to efficiently search the cost quality trade-off space of labeling and identify cost-efficient alternatives to labeling emails. Additionally, we design an on-demand provisioning scheme to intelligently scale Argo with real time load, to minimize cost increases during peak load inference. Over 3 open-source email datasets, Argo achieves 148-167X inference cost reduction with negligible quality degradation and 20-640000X lower profiling costs, making large-scale, context-aware email labeling practical for enterprises.