🏢
🌐 Entity
Catastrophic interference
AI's tendency to abruptly and drastically forget old info after learning new info
📊 Rating
1 news mentions · 👍 0 likes · 👎 0 dislikes
📌 Topics
- Artificial Intelligence (1)
- Machine Learning (1)
- Natural Language Processing (1)
🏷️ Keywords
Large Language Models (1) · Catastrophic Forgetting (1) · SA-SFT (1) · Self-Augmentation (1) · Fine-tuning (1) · Parameter Drift (1) · Self-Alignment (1) · Task-Specific Data (1)
📖 Key Information
Catastrophic interference, also known as catastrophic forgetting, is the tendency of an artificial neural network to abruptly and drastically forget previously learned information upon learning new information.
Neural networks are an important part of the connectionist approach to cognitive science. The issue of catastrophic interference when modeling human memory with connectionist models was originally brought to the attention of the scientific community by research from McCloskey and Cohen (1989), and Ratcliff (1990).
📰 Related News (1)
-
🇺🇸 Talking to Yourself: Defying Forgetting in Large Language Models
arXiv:2602.20162v1 Announce Type: cross Abstract: Catastrophic forgetting remains a major challenge when fine-tuning large language models (LLMs) on ...
🔗 Entity Intersection Graph
People and organizations frequently mentioned alongside Catastrophic interference:
-
🌐
Large language model · 1 shared articles