This talk demonstrates how Large Language Models (LLMs) can be used classifiers in large scale legal argument mining tasks. Through the example of the speaker’s recent work analyzing interpretive canon usage in the jurisprudence of the German Federal Constitutional Court, spanning 3,460 decisions and more than 17,000,000 words, we discuss how LLMs can perform tasks previously thought to require human-level understanding of legal argument patterns.

Time & Location

3 December 2024 | 6:00-7:30 p.m.

In-person & online
Rechtswissenschaften | Boltzmannstraße 3 | Room 4404
Join via: https://fu-berlin.webex.com/fu-berlin/j.php?MTID=mce94ae744470bdfd9118d5e925c8a542