No article text was recorded for this version.
layer-wise knowledge localization
Version 1 of 123 papers33 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Mr. Snuffleupagus at SemEval-2025 Task 4: Unlearning Factual Knowledge from LLMs Using Adaptive RMU
- Blog: RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models
- Blog: Decoupling Memories, Muting Neurons: Towards Practical Machine Unlearning for Large Language Models
- Blog: WAGLE: Strategic Weight Attribution for Effective and Modular Unlearning in Large Language Models
- Blog: Attention Smoothing Is All You Need For Unlearning
- Blog: MMUnlearner: Reformulating Multimodal Machine Unlearning in the Era of Multimodal Large Language Models
- Blog: Towards Robust and Parameter-Efficient Knowledge Unlearning for LLMs
- Blog: SHA256 at SemEval-2025 Task 4: Selective Amnesia – Constrained Unlearning for Large Language Models via Knowledge Isolation
- Blog: Align-then-Unlearn: Embedding Alignment for LLM Unlearning
- Blog: Unlearning Sensitive Information in Multimodal LLMs: Benchmark and Attack-Defense Evaluation
- Blog: RepSelect: Robust LLM Unlearning via Representational Selectivity
- Blog: ParamMute: Suppressing Knowledge-Critical FFNs for Faithful Retrieval-Augmented Generation
- Blog: Erasing Conceptual Knowledge from Language Models
- Blog: ULMR: Unlearning Large Language Models via Negative Response and Model Parameter Average
- Blog: PruneCD: Contrasting Pruned Self Model to Improve Decoding Factuality
- Blog: Module-Aware Parameter-Efficient Machine Unlearning on Transformers
- Blog: Get Confused Cautiously: Textual Sequence Memorization Erasure with Selective Entropy Maximization
- Blog: Dissecting Fine-Tuning Unlearning in Large Language Models
- Blog: Direct Token Optimization: A Self-contained Approach to Large Language Model Unlearning
- Blog: Dissecting Language Models: Machine Unlearning via Selective Pruning
- Blog: Fairness and Robustness in Machine Unlearning
- Blog: Targeted Unlearning with Single Layer Unlearning Gradient
- Blog: Correcting Language Model Outputs by Editing Salient Layers
History & citation
Current · Permanent link
- This direction split from catastrophic forgetting in unlearning (74% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_layer_wise_knowledge_localization_a5419207,
title = {layer-wise knowledge localization},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/layer-wise-knowledge-localization/rdr_a54192077e4f49aaa9ca2efdf4fd87b1},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}This exact version (version 1, frozen text):
@misc{lacuna_layer_wise_knowledge_localization_a5419207_v1,
title = {layer-wise knowledge localization},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/layer-wise-knowledge-localization/rdr_a54192077e4f49aaa9ca2efdf4fd87b1/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-19},
}