Tag
TRACE introduces a two-stage curriculum to preserve parametric tool knowledge in enterprise LLMs while enabling fast single-beam greedy decoding, achieving improved accuracy and recall over baselines.
Proposes Decompose-and-Refine (DaR), a framework for statute-grounded legal question answering that decomposes complex questions into atomic sub-questions and generates parametric queries for precise statutory retrieval, showing improvements on the KoBLEX benchmark.