LegalDrill uses diagnosis-driven synthesis and self-reflective verification to create high-quality training data that improves small language models' legal reasoning without expert annotations.
Follow the Reproduction Instruction to manipulate the logic (e.g., if instructed to ignore a condition, simply fail to mention it)
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
-
LegalDrill: Diagnosis-Driven Synthesis for Legal Reasoning in Small Language Models
LegalDrill uses diagnosis-driven synthesis and self-reflective verification to create high-quality training data that improves small language models' legal reasoning without expert annotations.