QA-TOOLBOX: Conversational Question-Answering for process task guidance in manufacturing

TL;DR

This paper investigates the use of large language models for data augmentation in a manufacturing process guidance system, focusing on complex task understanding and evaluating multiple open-source LLMs with expert and crowd-worker validation.

Contribution

It introduces a large dataset of manufacturing interactions and compares the performance of several open-source LLMs for task guidance and data augmentation.

Findings

LLMs can effectively augment manufacturing task data.

Performance varies significantly across different open-source LLMs.

Expert validation confirms the quality of LLM-generated responses.

Abstract

In this work we explore utilizing LLMs for data augmentation for manufacturing task guidance system. The dataset consists of representative samples of interactions with technicians working in an advanced manufacturing setting. The purpose of this work to explore the task, data augmentation for the supported tasks and evaluating the performance of the existing LLMs. We observe that that task is complex requiring understanding from procedure specification documents, actions and objects sequenced temporally. The dataset consists of 200,000+ question/answer pairs that refer to the spec document and are grounded in narrations and/or video demonstrations. We compared the performance of several popular open-sourced LLMs by developing a baseline using each LLM and then compared the responses in a reference-free setting using LLM-as-a-judge and compared the ratings with crowd-workers whilst validating the ratings with experts.