Weaving Pathways for Justice with GPT: LLM-driven automated drafting of interactive legal applications. Steenhuis, Q., Colarusso, D., & Willey, B. December, 2023. arXiv:2312.09198 [cs]
Paper doi abstract bibtex Can generative AI help us speed up the authoring of tools to help self-represented litigants? In this paper, we describe 3 approaches to automating the completion of court forms: a generative AI approach that uses GPT-3 to iteratively prompt the user to answer questions, a constrained template-driven approach that uses GPT-4-turbo to generate a draft of questions that are subject to human review, and a hybrid method. We use the open source Docassemble platform in all 3 experiments, together with a tool created at Suffolk University Law School called the Assembly Line Weaver. We conclude that the hybrid model of constrained automated drafting with human review is best suited to the task of authoring guided interviews.
@misc{steenhuisWeavingPathwaysJustice2023,
title = {Weaving {Pathways} for {Justice} with {GPT}: {LLM}-driven automated drafting of interactive legal applications},
shorttitle = {Weaving {Pathways} for {Justice} with {GPT}},
url = {http://arxiv.org/abs/2312.09198},
doi = {10.48550/arXiv.2312.09198},
abstract = {Can generative AI help us speed up the authoring of tools to help self-represented litigants? In this paper, we describe 3 approaches to automating the completion of court forms: a generative AI approach that uses GPT-3 to iteratively prompt the user to answer questions, a constrained template-driven approach that uses GPT-4-turbo to generate a draft of questions that are subject to human review, and a hybrid method. We use the open source Docassemble platform in all 3 experiments, together with a tool created at Suffolk University Law School called the Assembly Line Weaver. We conclude that the hybrid model of constrained automated drafting with human review is best suited to the task of authoring guided interviews.},
urldate = {2024-07-29},
publisher = {arXiv},
author = {Steenhuis, Quinten and Colarusso, David and Willey, Bryce},
month = dec,
year = {2023},
note = {arXiv:2312.09198 [cs]},
keywords = {Computer Science - Artificial Intelligence, Computer Science - Computers and Society, Computer Science - Social and Information Networks, Computer Science - Human-Computer Interaction, Computer Science - Computer Vision and Pattern Recognition},
}
Downloads: 0
{"_id":"YHasnEA3R5BkM66bt","bibbaseid":"steenhuis-colarusso-willey-weavingpathwaysforjusticewithgptllmdrivenautomateddraftingofinteractivelegalapplications-2023","author_short":["Steenhuis, Q.","Colarusso, D.","Willey, B."],"bibdata":{"bibtype":"misc","type":"misc","title":"Weaving Pathways for Justice with GPT: LLM-driven automated drafting of interactive legal applications","shorttitle":"Weaving Pathways for Justice with GPT","url":"http://arxiv.org/abs/2312.09198","doi":"10.48550/arXiv.2312.09198","abstract":"Can generative AI help us speed up the authoring of tools to help self-represented litigants? In this paper, we describe 3 approaches to automating the completion of court forms: a generative AI approach that uses GPT-3 to iteratively prompt the user to answer questions, a constrained template-driven approach that uses GPT-4-turbo to generate a draft of questions that are subject to human review, and a hybrid method. We use the open source Docassemble platform in all 3 experiments, together with a tool created at Suffolk University Law School called the Assembly Line Weaver. We conclude that the hybrid model of constrained automated drafting with human review is best suited to the task of authoring guided interviews.","urldate":"2024-07-29","publisher":"arXiv","author":[{"propositions":[],"lastnames":["Steenhuis"],"firstnames":["Quinten"],"suffixes":[]},{"propositions":[],"lastnames":["Colarusso"],"firstnames":["David"],"suffixes":[]},{"propositions":[],"lastnames":["Willey"],"firstnames":["Bryce"],"suffixes":[]}],"month":"December","year":"2023","note":"arXiv:2312.09198 [cs]","keywords":"Computer Science - Artificial Intelligence, Computer Science - Computers and Society, Computer Science - Social and Information Networks, Computer Science - Human-Computer Interaction, Computer Science - Computer Vision and Pattern Recognition","bibtex":"@misc{steenhuisWeavingPathwaysJustice2023,\n\ttitle = {Weaving {Pathways} for {Justice} with {GPT}: {LLM}-driven automated drafting of interactive legal applications},\n\tshorttitle = {Weaving {Pathways} for {Justice} with {GPT}},\n\turl = {http://arxiv.org/abs/2312.09198},\n\tdoi = {10.48550/arXiv.2312.09198},\n\tabstract = {Can generative AI help us speed up the authoring of tools to help self-represented litigants? In this paper, we describe 3 approaches to automating the completion of court forms: a generative AI approach that uses GPT-3 to iteratively prompt the user to answer questions, a constrained template-driven approach that uses GPT-4-turbo to generate a draft of questions that are subject to human review, and a hybrid method. We use the open source Docassemble platform in all 3 experiments, together with a tool created at Suffolk University Law School called the Assembly Line Weaver. We conclude that the hybrid model of constrained automated drafting with human review is best suited to the task of authoring guided interviews.},\n\turldate = {2024-07-29},\n\tpublisher = {arXiv},\n\tauthor = {Steenhuis, Quinten and Colarusso, David and Willey, Bryce},\n\tmonth = dec,\n\tyear = {2023},\n\tnote = {arXiv:2312.09198 [cs]},\n\tkeywords = {Computer Science - Artificial Intelligence, Computer Science - Computers and Society, Computer Science - Social and Information Networks, Computer Science - Human-Computer Interaction, Computer Science - Computer Vision and Pattern Recognition},\n}\n\n","author_short":["Steenhuis, Q.","Colarusso, D.","Willey, B."],"key":"steenhuisWeavingPathwaysJustice2023","id":"steenhuisWeavingPathwaysJustice2023","bibbaseid":"steenhuis-colarusso-willey-weavingpathwaysforjusticewithgptllmdrivenautomateddraftingofinteractivelegalapplications-2023","role":"author","urls":{"Paper":"http://arxiv.org/abs/2312.09198"},"keyword":["Computer Science - Artificial Intelligence","Computer Science - Computers and Society","Computer Science - Social and Information Networks","Computer Science - Human-Computer Interaction","Computer Science - Computer Vision and Pattern Recognition"],"metadata":{"authorlinks":{}}},"bibtype":"misc","biburl":"https://bibbase.org/f/vr5ooa48xeYes5KDD/ailaw.bib","dataSources":["7FkfQdR6FwGXEAZFa","QHxajSYCsDY5s5PEr"],"keywords":["computer science - artificial intelligence","computer science - computers and society","computer science - social and information networks","computer science - human-computer interaction","computer science - computer vision and pattern recognition"],"search_terms":["weaving","pathways","justice","gpt","llm","driven","automated","drafting","interactive","legal","applications","steenhuis","colarusso","willey"],"title":"Weaving Pathways for Justice with GPT: LLM-driven automated drafting of interactive legal applications","year":2023}