The paper reformulates industrial continual learning for LLMs as a closed-loop ecosystem problem, identifies three core challenges, and organizes solutions around five lifecycle design principles.
How to alleviate catastrophic forgetting in llms finetuning? hierarchical layer-wise and element-wise regularization
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 4verdicts
UNVERDICTED 4roles
background 1polarities
background 1representative citing papers
FINCH is a loss-adaptive learning-rate schedule that reduces forgetting by 93% on average during LLM fine-tuning while matching standard task performance across several benchmarks.
DualSFT derives parameter masks and data subsets as row- and column-wise aggregations of one gradient interaction matrix under first- and second-order validation-improvement approximations.
MedXIAOHE is a medical MLLM that claims state-of-the-art benchmark performance through specialized pretraining to cover long-tail diseases and RL-based reasoning training.
citing papers explorer
-
LLM Evolution as an Industry-Scale Ecosystem: A Lifecycle Perspective on Continual Learning
The paper reformulates industrial continual learning for LLMs as a closed-loop ecosystem problem, identifies three core challenges, and organizes solutions around five lifecycle design principles.
-
Fine-Tuning Without Forgetting via Loss-Adaptive Learning Rates
FINCH is a loss-adaptive learning-rate schedule that reduces forgetting by 93% on average during LLM fine-tuning while matching standard task performance across several benchmarks.
-
One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning
DualSFT derives parameter masks and data subsets as row- and column-wise aggregations of one gradient interaction matrix under first- and second-order validation-improvement approximations.
-
MedXIAOHE: A Comprehensive Recipe for Building Medical MLLMs
MedXIAOHE is a medical MLLM that claims state-of-the-art benchmark performance through specialized pretraining to cover long-tail diseases and RL-based reasoning training.