- Rating
- 3
- Confidence
- 4
- Informativeness
- 3
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper proposes GAP, a two-stage approach to constructing emulators for offsite-tuning large language models. The first stage perturbs the middle-layer weights while aligning adapter gradients with those of the original model at virtual update steps. The second stage removes low-importance layers using Block Influence. The goal is to improve the performance of the final plug-in model while maintaining a performance gap between the offsite and complete models. Experiments on several LLM backbones report improvements over existing offsite-tuning methods.
Critical strengths
-
The paper addresses a practical problem in offsite-tuning: how to weaken the shared emulator without making the learned adapters ineffective when transferred back to the original model. Focusing on adapter gradient alignment makes sense in this setting, since the adapters are what ultimately need to transfer. The two-stage method is also reasonably easy to follow.
-
The experimental results on Llama-3.2-3B and Llama-3.1-8B are encouraging, with average Plug-in improvements of 3.59 and 4.53 percentage points over OT. The paper also includes component ablations, compression-ratio comparisons, support-set analysis, and experiments on other model architectures, which help assess the method beyond a single setting.
Critical weaknesses
-
The benefit of the training-based perturbation is less clear than the paper suggests. In Table 3, removing gradient alignment reduces Plug-in performance by only 0.87 points, while replacing BI with uniform pruning causes a larger drop of 2.79 points. It is unclear how much of the improvement comes from the proposed gradient-aligned perturbation rather than layer selection.
-
The gap-utility trade-off is not consistently improved. On Qwen2.5-7B, GAP increases Plug-in performance from 59.36 to 61.16, but Offsite FTG drops from 11.39 to 3.85 compared with OT. A similar pattern appears on Qwen2.5-3B. These results weaken the claim that GAP can improve plug-in utility while maintaining larger performance gaps.
-
The theoretical analysis depends on assumptions that are difficult to verify in practice. In particular, the virtual adapter states are assumed to cover the downstream training region, and the gradient difference between support and downstream data is bounded. The paper does not show whether these assumptions hold during actual downstream fine-tuning.
-
The experimental comparison could be more convincing. The OT baseline omits its distillation stage, and ScaleOT is not included despite being discussed in related work. Also, the reported error bars reflect evaluation-sample uncertainty rather than variation across independent training runs, leaving the stability of the improvements unclear.
Questions for authors
-
How much does the gradient-aligned perturbation contribute when the layer selection is kept fixed? Would its advantage remain consistent across different random seeds and model architectures?
-
Why does GAP substantially reduce Offsite ZSG and FTG on the Qwen models while improving Plug-in performance? Is this trade-off sensitive to the perturbation strength or gradient alignment weight?
-
Does gradient alignment remain effective after pruning and throughout downstream fine-tuning? The current analysis mainly uses support-set gradients and local loss slices. How closely do these reflect the actual downstream training trajectories?
-
How would GAP compare against OT with its original distillation procedure and newer methods such as ScaleOT? Are the reported improvements stable across independent emulator construction and fine-tuning runs?