arXiv (All)
open access
A Step Towards Forgetting: Optimiser History and the Loss of Answer Mass
During fine-tuning, a language model can assign less probability to previously learned answers even when the current gradient acts to preserve that probability. With momentum, each update also carries gradients computed at earlier model states, and these stored contributions can push the model in th
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- When Forgetting is not Catastrophic: On the Mechanics of Spurious Forgetting#1218510
- When Forgetting is not Catastrophic: On the Mechanics of Spurious Forgetting#1210287
- Formalizing Forgetting: Theory of Forgetting for Online Continual Learning#1325683
- On remembering, forgetting, and understanding sentences#207542
- Catastrophic Forgetting is Low-Rank: A Function-Space Theory for Continual Adaptation#282797
Record · ID 1199214
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive