Can the Inference Logic of Large Language Models be Disentangled into Symbolic Concepts?

3 April 2023

Papers citing "Can the Inference Logic of Large Language Models be Disentangled into Symbolic Concepts?"

9 / 9 papers shown

Title
Technical Report: Quantifying and Analyzing the Generalization Power of a DNN Yuxuan He Junpeng Zhang Lei Cheng Hongyuan Zhang Quanshi Zhang AI4CE 26 0 0 11 May 2025
Evaluating the Correctness of Inference Patterns Used by LLMs for Judgment Lu Chen Yuxuan Huang Yixing Li Dongrui Liu Qihan Ren Shuai Zhao Kun Kuang Zilong Zheng Quanshi Zhang 34 1 0 06 Oct 2024
Layerwise Change of Knowledge in Neural Networks Xu Cheng Lei Cheng Zhaoran Peng Yang Xu Tian Han Quanshi Zhang KELM FAtt 35 5 0 13 Sep 2024
Quantifying In-Context Reasoning Effects and Memorization Effects in LLMs Siyu Lou Yuntian Chen Xiaodan Liang Liang Lin Quanshi Zhang 42 2 0 20 May 2024
Defining and Extracting generalizable interaction primitives from DNNs Lu Chen Siyu Lou Benhao Huang Quanshi Zhang 29 9 0 29 Jan 2024
Where We Have Arrived in Proving the Emergence of Sparse Symbolic Concepts in AI Models Qihan Ren Maximilian Brunner Wen Shen S. Mintchev 42 11 0 03 May 2023
Technical Note: Defining and Quantifying AND-OR Interactions for Faithful and Concise Explanation of DNNs Mingjie Li Quanshi Zhang 36 9 0 26 Apr 2023
Understanding and Unifying Fourteen Attribution Methods with Taylor Interactions Huiqi Deng Na Zou Mengnan Du Weifu Chen Guo-Can Feng Ziwei Yang Zheyang Li Quanshi Zhang FAtt TDI 57 22 0 02 Mar 2023
Discovering and Explaining the Representation Bottleneck of DNNs Huiqi Deng Qihan Ren Hao Zhang Quanshi Zhang 39 59 0 11 Nov 2021