Geonho Lee

Align, Then Correct: Training-Free Two-Stage Low-Rank Compensation for Extremely Quantized Large Language Models

Low-rank quantization error compensation (LQEC) recovers the accuracy lost under aggressive weight quantization by attaching a closed-form rank-$r$ adapter beside each frozen quantized weight, without any training. We show that existing compensators are limited by two shared simplifications. They calibrate symmetricall...

SafeQL: Search-based Refinement for Safe and E � icient LLM-based Text-to-SQL

SafeQL: Search-based Refinement for Safe and Efficient LLM-based Text-to-SQL

SafeQL is proposed, a search-based refinement paradigm that redefines the role of the DBMS as an active guide in the refinement process, and significantly improves execution accuracy and efficiency compared to regeneration-based methods.