arXiv:2610.08312v1 Announce Type: new Abstract: Continual learning (CL) is essential for Large Language Models (LLMs) to sequentially adapt to evolving tasks. To mitigate catastrophic forgetting, rec...
The paper introduces Subspace Tuning (SST), a fine‑tuning technique that restricts weight updates to the bottom singular subspace of model parameters, thereby protecting the principal directions that are most prone to catastrophic forgetting. SST is optimizer‑agnostic, works with existing fine‑tuning recipes such as SFT and self‑distillation, and includes dense gradient estimation and a refresh mechanism to enhance learning. Experiments show that SST can preserve up to 99 % of the weight subspace, significantly reduce KL drift, and nearly eliminate forgetting in large‑scale language models while maintaining strong target‑task performance.
The paper introduces LoDA, a LoRA-based continual learning method that decomposes update spaces into task‑shared and truly task‑specific subspaces using energy‑based objectives. By fixing down‑projections and learning up‑projections with Gradient‑Aligned Optimization, LoDA recalibrates general updates in closed form after each task, aiming to improve knowledge sharing and isolation. Experiments show that LoDA outperforms existing CL methods.
The paper introduces Subspace Tuning (SST), a fine‑tuning technique that confines weight updates to the bottom singular subspace of model parameters, thereby avoiding changes along principal directions that cause catastrophic forgetting. SST is optimizer‑agnostic, works with existing fine‑tuning recipes, and includes dense gradient estimation and a refresh mechanism. Experiments show that protecting up to 99% of the weight subspace significantly reduces forgetting, improves retention, and maintains strong target‑task performance, especially in large‑model regimes, while also reducing KL drift by 2–4× compared to baseline methods.
arXiv:2607. 16252v1 Announce Type: cross Abstract: Low-Rank Adaptation (LoRA) is a widely used parameter-efficient fine-tuning (PEFT) method for large language models.
arXiv:2608. 11674v1 Announce Type: cross Abstract: On-policy rollout methods such as GRPO are central to post-training of large language models, yet they frequently suffer from training instabilities, cross-task capability degradation, and response-length inflation.
arXiv:2606. 31813v1 Announce Type: cross Abstract: Low-rank adaptation (LoRA) and its variants enable parameter-efficient fine-tuning of large language models under the supervised fine-tuning (SFT) paradigm.
arXiv:2606. 10989v1 Announce Type: new Abstract: Large language model unlearning aims to suppress designated undesirable knowledge while preserving benign capabilities.
arXiv:2601. 09361v4 Announce Type: replace-cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) is a key paradigm for improving large-scale reasoning models.
ChainLoRA is a replay‑free continual learning framework for large language models that merges task vectors while preserving geometry. It uses chain‑updated training with a one‑sided orthogonality proxy to keep historical state and regularization overhead constant, and applies post‑stream adaptive SVD merging with Procrustes adaptation to separate shared and task‑specific components. Experiments demonstrate state‑of‑the‑art performance on Large and SuperNI benchmarks and competitive results on Standard CL, approaching the scores of replay‑based methods.
The paper introduces Continual Orthogonal Projection (COP), a gradient‑projection method that limits each unlearning update to the orthogonal complement of previously cached activation subspaces, thereby preventing interference between successive deletions. COP requires only a low‑rank basis per layer, avoiding the need for past gradients or previous forget sets, and can be applied to any differentiable‑loss unlearning method without altering its objective. Experiments on TOFU and RWKU benchmarks demonstrate that COP maintains model utility across sequential unlearning requests while preserving forgetting effectiveness and preventing collapse of standard objectives.
arXiv:2606. 31092v1 Announce Type: new Abstract: Full fine-tuning adapts large language models to new tasks but can erode capabilities they already possess.