conftrace_

parameter analysis

8 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (3) kernel invariance (1) knowledge behavior (1) capability localization (1) region partitioning (1) path integral (1) neuron localization (1) neural network (1) model knowledge (1) loss change allocation (1)

Papers

Analyzing the Effects of Supervised Fine-Tuning on Model Knowledge from Token and Parameter Levels EMNLP 2025 Capability Localization: Capabilities Can be Localized rather than Individual Knowledge ICLR 2025 Inferring Functionality of Attention Heads from their Parameters ACL 2025 Safety Layers in Aligned Large Language Models: The Key to LLM Security ICLR 2025 Unveiling Linguistic Regions in Large Language Models ACL 2024 Where do Models go Wrong? Parameter-Space Saliency Maps for Explainability NeurIPS 2022 Exchangeability and Kernel Invariance in Trained MLPs IJCAI 2019 LCA: Loss Change Allocation for Neural Network Training NeurIPS 2019