Language Model Interpretability and Empirical Legal Studies

Michael A. Livermore, Felix Herron and Daniel N. Rockmore

Journal of Institutional and Theoretical Economics (JITE), 2024, vol. 180, issue 2, 244-276

Abstract: Large language models (LLMs) now perform extremely well on many natural language processing tasks. Their ability to convert legal texts to data may offer empirical legal studies (ELS) scholars a low-cost alternative to research assistants in many contexts. However, less complex computational language models, such as topic modeling and sentiment analysis, are more interpretable than LLMs. In this paper we highlight these differences by comparing LLMs with less complex models on three ELS-related tasks. Our findings suggest that ELS research will - for the time being - benefit from combining LLMs with other techniques to optimize the strengths of each approach.

Keywords: empirical legal studies; natural language processing; interpretability; language models; computational analysis of law; law-as-data (search for similar items in EconPapers)
JEL-codes: K10 K40 K49 (search for similar items in EconPapers)
Date: 2024
References: Add references at CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
https://www.mohrsiebeck.com/en/article/language-mo ... 101628jite-2024-0009
Fulltext access is included for subscribers to the printed version.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:mhr:jinste:urn:doi:10.1628/jite-2024-0009

Ordering information: This journal article can be ordered from
Mohr Siebeck GmbH & Co. KG, P.O.Box 2040, 72010 Tübingen, Germany

DOI: 10.1628/jite-2024-0009

Access Statistics for this article

Journal of Institutional and Theoretical Economics (JITE) is currently edited by Gerd Mühlheußer and Bayer, Ralph-C

More articles in Journal of Institutional and Theoretical Economics (JITE) from Mohr Siebeck, Tübingen
Bibliographic data for series maintained by Thomas Wolpert ().