Task-aware Block Pruning with Output Distribution Signals for Large Language Models

Song-ha Jo, Youngrok Ko, Sang-goo Lee, Jinseok Seol. Task-aware Block Pruning with Output Distribution Signals for Large Language Models. In Vera Demberg, Kentaro Inui, LluĂ­s Marquez, editors, Findings of the Association for Computational Linguistics: EACL 2026, Rabat, Morocco, March 24-29, 2026. pages 6089-6107, Association for Computational Linguistics, 2026. [doi]

Abstract

Abstract is missing.