LePREC combines LLM-generated analytical QA factors with sparse linear classification to achieve 30-40% better precision than pure LLMs in identifying relevant legal issues from court cases.
Generated Issue Candidates Given Scenario#2:
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
LePREC: Reasoning as Classification over Structured Factors for Assessing Relevance of Legal Issues
LePREC combines LLM-generated analytical QA factors with sparse linear classification to achieve 30-40% better precision than pure LLMs in identifying relevant legal issues from court cases.