Summary of Qa-toolbox: Conversational Question-answering For Process Task Guidance in Manufacturing, by Ramesh Manuvinakurike et al.
QA-TOOLBOX: Conversational Question-Answering for process task guidance in manufacturing
by Ramesh Manuvinakurike, Elizabeth Watkins, Celal Savur, Anthony Rhodes, Sovan Biswas, Gesem Gudino Mejia, Richard Beckwith, Saurav Sahay, Giuseppe Raffa, Lama Nachman
First submitted to arxiv on: 3 Dec 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper explores utilizing Large Language Models (LLMs) for data augmentation in manufacturing task guidance systems. It focuses on evaluating the performance of existing LLMs in supporting complex tasks that require understanding procedure specification documents, actions, and objects sequenced temporally. The dataset consists of over 200,000 question-answer pairs grounded in narrations and/or video demonstrations. Various popular open-sourced LLMs are compared by developing a baseline using each model and then evaluating their responses in a reference-free setting. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This study uses Large Language Models to help guide technicians in manufacturing settings. It looks at how well these models can learn from data and make predictions about complex tasks that require understanding documents, actions, and objects. The team collected over 200,000 examples of questions and answers related to these tasks, which will be used to test the models’ abilities. |
Keywords
» Artificial intelligence » Data augmentation
