SyncAI.news, a Varaisys broadcasting
Reasoning-Preserving Fine-Tuning of Post-RL LLMs with Null-Basis LoRA
WF

Wenzhi Fang, Nicholas Tzou, Lazar Valkov, Srinivas Chappidi

· 1 min read

ResearcharXiv cs.AI

Reasoning-Preserving Fine-Tuning of Post-RL LLMs with Null-Basis LoRA

arXiv:2609.25618v1 Announce Type: new Abstract: Reinforcement learning (RL)-based post-training has become an effective approach for eliciting reasoning capabilities in large language models (LLMs). However, adapting post-RL models to new knowledge domains or behaviors through subsequent supervised fine-tuning (SFT) can severely overwrite these capabilities. Existing approaches mitigate such forgetting through experience replay, specialized initialization, or constrained optimization using gradient projection, but either provide limited preservation or incur substantial training overhead. Our analysis shows that reasoning activations concentrate in low-dimensional subspaces, leaving substantial null-space capacity for adaptation, and that the corresponding approximate null spaces can be reliably estimated from a modest number of examples. Motivated by these observations, we propose Null-Basis Low-Rank Adaptation (NB-LoRA), a parameter-efficient method for adapting post-RL LLMs while preserving their acquired reasoning ability. We formulate reasoning retention as a layer-wise hidden-state preservation constraint and construct a fixed approximate null basis from reasoning activations. LoRA updates are then reparameterized through this basis, enforcing the preservation constraint throughout fine-tuning. Extensive experiments across multiple RL-trained LLMs and diverse downstream tasks show that NB-LoRA matches standard LoRA in adaptation performance, maintains reasoning accuracy near pre-fine-tuning levels, and generalizes this preservation to held-out reasoning benchmarks.

Original source

This story was published by arXiv cs.AI and written by Wenzhi Fang, Nicholas Tzou, Lazar Valkov, Srinivas Chappidi. SyncAI.news shows a preview; the complete article is on the publisher's site.

Read the full story on arxiv.org

Similar News