Journal: Journal of Empirical Legal Studies

Abbreviation

Publisher

Wiley

Journal Volumes

ISSN

1740-1453
1740-1461

Description

Filters

2017 - 201912020 - 20242
Reset filters

Search Results

Publications 1 - 3 of 3
  • Building a better lawyer: Experimental evidence that artificial intelligence can increase legal work efficiency
    Item type: Journal Article
    Nielsen, Aileen; Skylaki, Stavroula; Norkute, Milda; et al. (2024)
    Journal of Empirical Legal Studies
    Rapidly improving artificial intelligence (AI) technologies have created opportunities for human-machine cooperation in legal practice. We provide evidence from an experiment with law students (N = 206) on the causal impact of machine assistance on the efficiency of legal task completion in a private law setting with natural language inputs and multidimensional AI outputs. We tested two forms of machine assistance: AI-generated summaries of legal complaints and AI-generated text highlighting within those complaints. AI-generated highlighting reduced task completion time by 30% without any reduction in measured quality indicators compared to no AI assistance. AI-generated summaries produced no change in performance metrics. AI summaries and AI highlighting together improved efficiency but not as much as AI highlighting alone. Our results show that AI support can dramatically increase the efficiency of legal task completion, but finding the optimal form of AI assistance is a fine tuning exercise. Currently, AI-generated highlighting is not readily available from state-of-the-art, consumer-facing large language models, but our work suggests that this capability should be prioritized in the development of legal AI products.
  • Automating Abercrombie: Machine-Learning Trademark Distinctiveness
    Item type: Journal Article
    Adarsh, Shivam; Ash, Elliott; Bechtold, Stefan; et al. (2024)
    Journal of Empirical Legal Studies
    Trademark law protects marks to enable firms to signal their products' qualities to consumers. To qualify for protection, a mark must be able to identify and distinguish goods. US courts typically locate a mark on a “spectrum of distinctiveness”—known as the Abercrombie spectrum—that categorizes marks as fanciful, arbitrary, or suggestive, and thus as “inherently distinctive,” or as descriptive or generic, and thus as not inherently distinctive. This article explores whether locating trademarks on the Abercrombie spectrum can be automated using current natural-language processing techniques. Using about 1.5 million US trademark registrations between 2012 and 2019 as well as 2.2 million related USPTO office actions, the article presents a machine-learning model that learns semantic features of trademark applications and predicts whether a mark is inherently distinctive. Our model can predict trademark actions with 86% accuracy overall, and it can identify subsets of trademark applications where it is highly certain in its predictions of distinctiveness. Using an eXplainable AI (XAI) algorithm, we further analyze which features in trademark applications drive our model's predictions. We then explore the practical and normative implications of our approach. On a practical level, we outline a decision-support system that could, as a “robot trademark clerk,” assist trademark experts in their determination of a trademark's distinctiveness. Such a system could also help trademark experts understand which features of a trademark application contribute the most toward a trademark's distinctiveness. On a theoretical level, we discuss the normative limits of the Abercrombie spectrum and propose to move beyond Abercrombie for trademarks whose distinctiveness is uncertain. We discuss how machine-learning projects in the law not only inform us about the aspects of the legal system that may be automated in the future, but also force us to tackle normative tradeoffs that may be invisible otherwise.
Publications 1 - 3 of 3