The authors present LRI, a task and benchmark for inducing legal rules from analogous Chinese judicial precedents, and show that fine-tuning improves LLM performance significantly.
If [Hypothetical condition], then [behavioral pattern], then/otherwise [legal consequence]
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Legal Rule Induction: Towards Generalizable Principle Discovery from Analogous Judicial Precedents
The authors present LRI, a task and benchmark for inducing legal rules from analogous Chinese judicial precedents, and show that fine-tuning improves LLM performance significantly.