technique

Language Model Finetuning

techniqueactiveprovisionallanguage-model-finetuning-92fe361d·1 events·first seen 22d ago

Aliases: Language Model Finetuning

Co-occurring entities

catastrophic forgetting Continual Learning Self-Generated Replay

More like this (12)

Language Modeling Loss Language Model Safety Monitor Transformer Language Models Parameter-Efficient Fine-Tuning Test-Time Finetuning (TTFT)A Unifying Lens on Supervised Fine-Tuning Through Target Distribution Design Decomposing Factual Sycophancy in Language Models: How Size and Instruction Tuning Shape Robustness multi-turn language models Fine-tuning GPT-2 from Human Preferences Chain-of-Thought Fine-Tuning encoder-only language models OpenAI Fine-Tuning

Recent events (1)

6arXiv · cs.LG·22d ago·source ↗

Self-Generated Replay Nearly Eliminates Catastrophic Forgetting in Language Models

This paper investigates catastrophic forgetting in language models during continual learning, finding that models can use self-generated samples from their own training distribution as effective replay data, nearly eliminating forgetting without requiring stored exemplars. The authors identify two key conditions where forgetting persists: when models are pretrained near capacity saturation (leaving no room for new knowledge), and when low learning rates are used to reduce forgetting at the cost of requiring far more training steps. Self-generated replay breaks this learning-rate/forgetting tradeoff, enabling fast high-learning-rate finetuning without degradation on prior tasks.

Enterprise Deployment Patterns Agent and Tool Ecosystem catastrophic forgetting Language Model Finetuning Continual Learning +2 more