Language Model Interpretability and Empirical Legal Studies
Bibliographic Data
| ID | 24037014 |
|---|---|
| Authors | Michael A Livermore (0000-0002-2403-1173), Felix Herron, Daniel N Rockmore (0000-0001-5411-9224) |
| Year | 2024 |
| Volume | 180 |
| Issue | 2 |
| Pages | 244-276 |
| Publication date | 2024-01-01 |
| Open Access | No |
| Type | ARTICLE |
| Venue | Journal of Institutional and Theoretical Economics JITE (JOURNAL) |
| Journal identifiers | ISSN: 0932-4569 • E-ISSN: 1614-0559 |
| Publisher | Mohr Siebeck (PUBLISHER) |
| DOI | 10.1628/jite-2024-0009 |
| OpenAlex | W4400926486 |
| Language | EN |
| Citations received | 2 |
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.
Empirical research · Interpretability · Natural language processing · Statistics · Artificial Intelligence · Comparative and International Law Studies · Computer Science · European and International Law Studies · Legal Language and Interpretation · Mathematics
| Citations per year | 2 |
|---|---|
| Citation span | 2025 - 2025 (1) |
| Highly cited | No |