circuit-preservation

Tag

Cards List
#circuit-preservation

Mechanistic origins of catastrophic forgetting: why RL preserves circuits better than SFT?

arXiv cs.LG · 2026-05-29 Cached

This paper investigates the mechanistic origins of catastrophic forgetting in LLMs, finding that reinforcement learning preserves internal computational circuits better than supervised fine-tuning, resulting in less forgetting of prior capabilities.

0 favorites 0 likes
← Back to home

Submit Feedback