Unveiling Instruction-Specific Neurons & Experts: An Analytical Framework for LLM's Instruction-Following Capabilities

27 May 2025

Papers citing "Unveiling Instruction-Specific Neurons & Experts: An Analytical Framework for LLM's Instruction-Following Capabilities"

6 / 6 papers shown

Title
ErrorRadar: Benchmarking Complex Mathematical Reasoning of Multimodal Large Language Models Via Error Detection Yibo Yan Shen Wang Jiahao Huo Hang Li Yangqiu Song ... Kun Wang Hui Xiong Philip S. Yu Xuming Hu Qingsong Wen LRM 46 17 0 06 Oct 2024
Sharing Matters: Analysing Neurons Across Languages and Tasks in LLMs Weixuan Wang Barry Haddow Wei Peng Alexandra Birch MILM 48 14 0 13 Jun 2024
Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey Zeyu Han Chao Gao Jinyang Liu Jeff Zhang Sai Qian Zhang 172 345 0 21 Mar 2024
Circuit Component Reuse Across Tasks in Transformer Language Models Jack Merullo Carsten Eickhoff Ellie Pavlick 53 66 0 12 Oct 2023
Qwen Technical Report Jinze Bai Shuai Bai Yunfei Chu Zeyu Cui Kai Dang ... Zhenru Zhang Chang Zhou Jingren Zhou Xiaohuan Zhou Tianhang Zhu OSLM 110 1,709 0 28 Sep 2023
TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension Mandar Joshi Eunsol Choi Daniel S. Weld Luke Zettlemoyer RALM 116 2,576 0 09 May 2017