No article text was recorded for this version.
pre-training knowledge resilience
Version 1 of 121 papers39 conceptsfrozen 2026-10-04
Papers in this version
- Blog: PULSE: Practical Evaluation Scenarios for Large Multimodal Model Unlearning
- Blog: KnowledgeSmith: Uncovering Knowledge Updating in LLMs with Model Editing and Unlearning
- Blog: Understanding Fine-tuning in Approximate Unlearning: A Theoretical Perspective
- Blog: Unveiling Entity-Level Unlearning for Large Language Models: A Comprehensive Analysis
- Blog: Fast-NTK: Parameter-Efficient Unlearning for Large-Scale Models
- Blog: Do Unlearning Methods Remove Information from Language Model Weights?
- Blog: Approximate Domain Unlearning for Vision-Language Models
- Blog: Investigating Memorization in Video Diffusion Models
- Blog: Can Large Language Models Truly Forget Scientific Claims? A Systematic Evaluation of Claim Level Unlearning
- Blog: Does Machine Unlearning Truly Remove Knowledge?
- Blog: Fine-tuned Language Models are Continual Learners
- Blog: Editing as Unlearning: Are Knowledge Editing Methods Strong Baselines for Large Language Model Unlearning?
- Blog: You Don’t Need All That Attention: Surgical Memorization Mitigation in Text-to-Image Diffusion Models
- Blog: Revisiting the Past: Data Unlearning with Model State History
- Blog: Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks
- Blog: The Phantom Menace: Unmasking Privacy Leakages in Vision-Language Models
- Blog: Provable unlearning in topic modeling and downstream tasks
- Blog: Why Fine-Tuning Struggles with Forgetting in Machine Unlearning? Theoretical Insights and a Remedial Approach
- Blog: Measuring memorization in RLHF for code completion
- Blog: Not All Data Are Unlearned Equally
- Blog: Outdated Issue Aware Decoding for Factual Knowledge Editing
History & citation
Current · Permanent link
- This direction split from The Persistence of Pre-trained Knowledge in Large Language Models (71% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_pre_training_knowledge_resilience_293cdf65,
title = {pre-training knowledge resilience},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/pre-training-knowledge-resilience/rdr_293cdf65831642868ba258621db1556e},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-21},
}This exact version (version 1, frozen text):
@misc{lacuna_pre_training_knowledge_resilience_293cdf65_v1,
title = {pre-training knowledge resilience},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/pre-training-knowledge-resilience/rdr_293cdf65831642868ba258621db1556e/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-21},
}