conftrace_

neuron attribution

8 papers

Explore in graph

Also known as

NA

Co-occurring keywords · papers mentioning both

large language model (3) knowledge editing (3) multimodal large language model (2) language model (2) social bias mitigation (1) query-relevant neuron (1) training instance (1) fuzzy set theory (1) feature-level attack (1) cross-modal invariance (1)

Papers

Attribution and Application of Multiple Neurons in Multimodal Large Language Models EMNLP 2025 Identifying Query-Relevant Neurons in Large Language Models for Long-Form Texts AAAI 2025 Mechanistic Understanding and Mitigation of Language Confusion in English-Centric Large Language Models EMNLP 2025 Neuron-Level Knowledge Attribution in Large Language Models EMNLP 2024 Revealing the Parametric Knowledge of Language Models: A Unified Framework for Attribution Methods ACL 2024 The Devil is in the Neurons: Interpreting and Mitigating Social Biases in Language Models ICLR 2024 Towards Neuron Attributions in Multi-Modal Large Language Models NeurIPS 2024 Improving Adversarial Transferability via Neuron Attribution-Based Attacks CVPR 2022