Why Fine-Tuned Memories Still Struggle to Generalize
burny_tech · x · 2026-07-13
This paper examines a common phenomenon: LLMs can quickly memorize new facts during fine-tuning, but generalize poorly when multi-hop reasoning is required.
The author suggests the issue isn't "failure to learn knowledge," but a misalignment between knowledge and reasoning circuits. While facts exist inside the model, they don't reside in the layers actively involved in reasoning. By using self-patching to move appropriate hidden representations to the correct layers, the paper restored a significant portion of generalization ability; a simple heuristic recovered 58–75% of the oracle headroom.
Related event: Study Reveals Knowing-Using Gap in LLM Fine-Tuning(2 posts)→
More from Models
- Fable 5.5 launch rumors persist for third week, but no frontier model drops this month — patience_cave · 2026-10-26
- Abliterated Model Flops in the Wild: It Got Worried About My Mental Health Instead — ryunuck · 2026-10-26
- OpenAI upgrades Decisions API: 400 questions per call, native voice and image support — OpenAIDevs · 2026-10-26
- Fangcun AI, China's first independent frontier AI safety lab, launches with DeepSeek eval report — JacquesThibs · 2026-10-26
- When AI hits an existential crisis: model confuses itself and everyone else — Ok-Delivery-7437 · 2026-10-26
- Kimi K3.1 Pro tops MathArena open models, closing frontier gap to about 6 months — teortaxesTex · 2026-10-26