Do Multimodal Foundation Models Understand Enterprise Workflows? A Benchmark for Business Process Management Tasks

Existing ML benchmarks lack the depth and diversity of annotations needed for evaluating models on business process management (BPM) tasks. BPM is the practice of documenting, measuring, improving, and automating enterprise workflows. However, research has focused almost exclusively on one task - full end-to-end automation using agents based on multimodal foundation models (FMs) like GPT-4. This focus on automation ignores the reality of how most BPM tools are applied today - simply documenting the relevant workflow takes 60% of the time of the typical process optimization project. To address this gap we present WONDERBREAD, the first benchmark for evaluating multimodal FMs on BPM tasks beyond automation. Our contributions are: (1) a dataset containing 2928 documented workflow demonstrations; (2) 6 novel BPM tasks sourced from real-world applications ranging from workflow documentation to knowledge transfer to process improvement; and (3) an automated evaluation harness. Our benchmark shows that while state-of-the-art FMs can automatically generate documentation (e.g. recalling 88% of the steps taken in a video demonstration of a workflow), they struggle to re-apply that knowledge towards finer-grained validation of workflow completion (F1 < 0.3). We hope WONDERBREAD encourages the development of more "human-centered" AI tooling for enterprise applications and furthers the exploration of multimodal FMs for the broader universe of BPM tasks. We publish our dataset and experiments here: https://github.com/HazyResearch/wonderbread

General Line Coordinates in 3D

Interpretable interactive visual pattern discovery in lossless 3D visualization is a promising way to advance machine learning. It enables end users who are not data scientists to take control of the model development process as a self-service. It is conducted in 3D General Line Coordinates (GLC) visualization space, which preserves all n-D information in 3D. This paper presents a system which combines three types of GLC: Shifted Paired Coordinates (SPC), Shifted Tripled Coordinates (STC), and General Line Coordinates-Linear (GLC-L) for interactive visual pattern discovery. A transition from 2-D visualization to 3-D visualization allows for a more distinct visual pattern than in 2-D and it also allows for finding the best data viewing positions, which are not available in 2-D. It enables in-depth visual analysis of various class-specific data subsets comprehensible for end users in the original interpretable attributes. Controlling model overgeneralization by end users is an additional benefit of this approach.