The paper investigates how supervised fine‑tuning (SFT) affects different layers of language models, finding that middle layers (20–80%) remain stable while the final layers are highly sensitive to changes. Using information‑theoretic, geometric, and optimization metrics across 1B‑32B models, the authors identify a depth‑dependent pattern and introduce Mid‑Block Efficient Tuning, which updates only the critical intermediate layers. Experiments show this method outperforms standard LoRA by up to 10.2 % on GSM8K (OLMo2‑7B) with lower parameter overhead, suggesting that alignment can be achieved with localized architectural changes.
arXiv:2608. 19800v1 Announce Type: cross Abstract: Low-Rank Adaptation (LoRA) is a prominent fine-tuning method for large models, achieving competitive performance with reduced memory overhead.
arXiv:2610.07553v1 Announce Type: cross Abstract: LoRA fine-tuning adapts small language models (SLMs) to heterogeneous instruction data within a low-rank update subspace, making it vulnerable to thr...
arXiv:2610.34756v1 Announce Type: cross Abstract: Low-Rank Adaptation (LoRA) has emerged as the dominant paradigm for parameter-efficient fine-tuning of large language models. Standard all-layer LoRA...
arXiv:2606. 05516v1 Announce Type: new Abstract: Zeroth-order (ZO) optimization enables memory-efficient fine-tuning of large language models (LLMs) using only forward passes, but it remains unclear how useful adaptation is distributed across layers.
The paper investigates how memorization behaves during fine‑tuning of large language models with LoRA, a parameter‑efficient technique. It finds that LoRA fine‑tuning diverges from previous results seen in full fine‑tuning and pre‑training: factors like model size and data duplication no longer predict memorization in the same way. Using a relaxed similarity‑based metric, the authors show that LoRA substantially lowers memorization risk while preserving strong task performance.
arXiv:2606. 14970v1 Announce Type: new Abstract: Fine-tuning large language models (LLMs) has become a central application of modern optimization, enabling pretrained models to adapt to diverse downstream tasks and domain-specific data.
arXiv:2607. 08733v1 Announce Type: new Abstract: Recent work identified Super Weights, individual parameters whose removal degrades model performance by orders of magnitude.
The paper introduces SSR, a simple yet effective data selection strategy for million‑scale multi‑modal instruction‑tuning. SSR uses interaction styles as a proxy for structural diversity and decomposes data quality into capability‑specific scores, forming a rich profile for each sample. By casting selection as submodular coverage maximization, SSR consistently outperforms random sampling across two architecture stacks, multiple data pools, and 14 benchmarks, achieving 99.1% of full‑data performance with only 30% of a 2.6M pool.
arXiv:2608. 05161v1 Announce Type: cross Abstract: Instruction-tuned LLMs are deployed into environments where domains evolve, yet extending a fine-tuned model's capabilities without full retraining remains an unsolved practical challenge.
arXiv:2602. 14696v2 Announce Type: replace Abstract: Instruction fine-tuning of large language models (LLMs) often involves selecting a subset of instruction training data from a large candidate pool, using a small query set from the target task.
The paper introduces Ladder Side Tuning (LST), a parameter‑efficient fine‑tuning method that adds a lightweight side network to large language models. LST matches QLoRA’s compute scaling while halving peak memory usage, enabling 7B‑parameter models to be fine‑tuned on a single 12 GB GPU with 2k‑token contexts without gradient checkpointing. The authors also present xLadder, a depth‑extended variant that increases effective depth through cross‑connections, allowing deeper reasoning without extra memory overhead.
arXiv:2607. 11940v1 Announce Type: cross Abstract: As the scale of large pre-trained models continues to grow, fine-tuning them under limited memory budgets has become increasingly challenging.