- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
AGFT is a continual fine-tuning method for LLMs. It first fine-tunes a separate copy of the model on each task and attributes the predicted logit to individual parameters. During sequential training, it then scales down gradients on parameters that were important to earlier tasks. It is evaluated on different continual-learning benchmarks and on Llama and Qwen backbones of different sizes.
Critical strengths
- The evaluation is broad, covering more than one benchmark, backbones of different families and sizes, both full fine-tuning and LoRA, and baselines from several kinds of continual-learning methods.
- The attribution scores pass a clear sanity check: masking the top-ranked parameters hurts much more than masking random ones.
Critical weaknesses
- The gains rest on a single run. All experiments use one fixed seed, with no variance reported. On TRACE, the lead over the strongest replay baseline is under a point for both fully fine-tuned models.
- The paper calls the starting point a pretrained or base LLM, but one backbone is instruction-tuned while the others appear to be base models. This choice is not discussed, although an instruction-tuned model may forget differently from a base one. The smaller models also use full fine-tuning and the larger ones LoRA, so the effect of model size cannot be told apart from that of the fine-tuning mode.
Questions for authors
- Can you report mean and variance over several seeds?
- Which backbones are base models and which are instruction-tuned, and why are they mixed?
- How does AGFT do with LoRA on the smaller models, or with full fine-tuning on a larger one?
4 comments
Thank you for the response.
- The two-seed results on Concept-1K help, and AGFT stays ahead in all four settings. TRACE is still a single run, and I understand the cost issue you mention.
- The answer on base and instruction-tuned backbones is clear, and the memory limit explains why the 7B models use LoRA. Model size and fine-tuning mode are still tied together, though, so their effects cannot be separated.
- Protecting important parameters is already common in continual learning, for example EWC, and Child-Tuning (Xu et al., EMNLP 2021) uses a similar gradient mask in standard fine-tuning. The main new part of AGFT is the attribution score, so I see the novelty as limited. For these reasons I keep my score.
Reply to Reviewer (1)
Q1: Protecting important parameters is already common in continual learning, for example EWC, and Child-Tuning (Xu et al., EMNLP 2021) uses a similar gradient mask in standard fine-tuning. The main new part of AGFT is the attribution score, so I see the novelty as limited.
A1: Thanks for your reply. We would like to clarify that the novelty of AGFT does not lie in gradient masking itself, but in how parameter importance is defined, estimated, analyzed, and exploited for continual learning in LLMs.
(1) Difference from EWC [1]. EWC estimates parameter importance using the diagonal Fisher Information Matrix (FIM). It measures the local sensitivity of the predictive distribution to parameter perturbations and uses a quadratic penalty to discourage changes to important parameters. In contrast, AGFT quantifies parameter importance from a fundamentally different perspective: the direct contribution of individual parameters to next-token predictions. Specifically, we extend Layer-wise Relevance Propagation (LRP) to Transformer architectures and derive parameter-level relevance propagation rules for both self-attention and FFN modules. Thus, AGFT identifies which individual parameters contribute to task-specific predictions, rather than relying on gradient-based sensitivity as a proxy for importance.
Moreover, estimating Fisher importance introduces additional computational and memory overhead, particularly for LLMs with large parameter spaces and long input sequences. In our experiments, we encountered CUDA out-of-memory (OOM) errors when estimating Fisher information on long-sequence examples from the TRACE dataset. This limitation highlights an important scalability challenge of Fisher-based importance estimation for continual learning in LLMs.
More importantly, on concept-1k dataset, as reported in Table 2 of our previous response, AGFT consistently outperforms EWC across all four model configurations, achieving improvements of 10.30, 5.19, 5.32, and 2.93 percentage points, respectively, with an average improvement of 5.94 percentage points across the four settings. These results demonstrate the effectiveness of our attribution-based parameter importance estimation compared with Fisher-based importance estimation.
(2) Difference from Child-Tuning. Child-Tuning employs binary gradient masks to select a subset of parameters for updating, whereas AGFT derives continuous, element-wise gradient masks from attribution-based parameter importance scores. However, gradient masking itself is not the primary methodological novelty of our work. Our key novelty lies in identifying task-relevant parameters through LRP-based attribution and leveraging their importance to guide continual learning.
To further disentangle the effects of gradient modulation from those of parameter importance estimation, we conducted additional controlled experiments in response to Reviewer xd5j. we conducted two additional controlled experiments:
-
1 Random Importance: We randomly generate parameter importance scores and apply the same normalization, gradient mask construction, and parameter update procedure as AGFT.
-
2 Shuffled Importance: We shuffle AGFT's estimated importance scores across model parameters, disrupting their correspondence with specific parameter locations, while retaining the same score distribution. We then apply the same gradient modulation procedure as AGFT.
All other experimental settings remain identical to AGFT. These comparisons allow us to examine whether the performance gains result from accurately identifying important parameters or merely from applying gradient masking.
Table 3. Controlled comparison on Concept-1K.
| Method | Qwen2.5-3B (Full) | Qwen2.5-7B (LoRA) | Llama-3.2-3B (Full) | Llama-2-7B (LoRA) |
|---|---|---|---|---|
| AGFT (Ours) | 28.292 | 24.476 | 26.336 | 23.707 |
| Random | 24.700 | 21.328 | 20.872 | 16.666 |
| Shuffle | 27.653 | 22.738 | 23.911 | 22.371 |
Table 4. Controlled comparison on TRACE.
| Method | Qwen2.5-3B (Full) | Qwen2.5-7B (LoRA) | Llama-3.2-3B (Full) | Llama-2-7B (LoRA) |
|---|---|---|---|---|
| AGFT (Ours) | 54.922 | 54.745 | 54.880 | 47.775 |
| Random | 53.020 | 52.778 | 49.431 | 39.661 |
| Shuffle | 53.477 | 54.127 | 51.939 | 46.445 |
Results and Analysis. Tables 3 and 4 show that AGFT outperforms Random and Shuffled Importance on all four models across both benchmarks. On Concept-1K, AGFT averages 25.703, exceeding Random and Shuffled Importance by 4.811 and 1.535 points, respectively. On TRACE, AGFT averages 53.081, with gains of 4.358 and 1.584 points, respectively. These results suggest that AGFT's gains from parameter importance scores, not gradient masking alone.
Reply to Reviewer (2)
(3) Further clarification of AGFT's novelty. We would like to emphasize three contributions that go beyond applying an existing gradient mask:
Parameter-level attribution for LLMs. We derive LRP-based relevance propagation rules for Transformer architectures, covering both self-attention and FFN modules, to quantify the contribution of individual parameters to next-token predictions.
Analysis of task-dependent parameter overlap. We investigate the overlap of important parameters across different tasks and Transformer layers, revealing how parameter importance is shared among related tasks and differs across dissimilar tasks.
Attribution-guided continual learning. We leverage the estimated parameter-level contributions to characterize knowledge acquired from previous tasks and construct historical importance priors. These priors enable selective protection of parameters critical to previously learned behaviors while preserving the flexibility of less important parameters for new-task adaptation.
In summary, AGFT makes a contribution by introducing Transformer-specific parameter-level attribution, uncovering task-dependent parameter importance patterns, and leveraging these attribution scores to guide knowledge preservation in continual LLM fine-tuning. Our additional controlled experiments further demonstrate that the performance gains cannot be attributed merely to gradient masking, but critically depend on accurately identifying task-important parameter locations through our attribution mechanism.
Response to Reviewer
Thank you for taking the time to review our paper!
A1: Regarding model initialization, we use four backbones: Llama-3.2-3B-Instruct, Qwen2.5-3B, Llama-2-7B, and Qwen2.5-7B. Among them, only Llama-3.2-3B-Instruct is instruction-tuned, while the other three are base models. Our intention is to evaluate AGFT across different model families and initialization settings. Using heterogeneous initialization settings is also not without precedent in recent continual learning research. For example, [1] evaluates Llama-3.2-3B (base) on Merge and Llama-3.2-3B-Instruct on TRACE. These studies demonstrate the relevance of evaluating continual learning methods across different model initialization settings.
[1] Merge to Remember: Sharpness-Aware Isotropic Merging for Continual Learning. Forty-third International Conference on Machine Learning.
A2: Our experiments were conducted on NVIDIA A6000 GPUs with 48 GB of memory. Under our experimental settings, full-parameter fine-tuning of 7B models resulted in CUDA out-of-memory errors. We conducted additional experiments using LoRA fine-tuning on two models, Llama-3.2-3B-Instruct and Qwen2.5-3B on concept-1k dataset. As shown in Table 1, AGFT outperforms all competing baselines. Specifically, compared with the strongest baseline, DER++, AGFT achieves improvements of 2.082 and 1.773 points on the two models, respectively. These additional results demonstrate that AGFT remains effective when LoRA fine-tuning is applied to smaller models
Table 1. Performance Comparison of Different Methods with LoRA Fine-Tuning on Concept-1K.
A3: Due to limited computational resources and the short rebuttal timeline, we conducted additional multi-seed experiments on Concept-1K across all four model configurations and report the corresponding mean and standard deviation. However, running multiple seeds on TRACE is considerably more expensive, as training each method on this benchmark requires substantially more time. Therefore, we were unable to complete multi-seed experiments for TRACE within the rebuttal period.
Table 2. Results on Concept-1K (Mean ± Std over Two Seeds).
As shown in Table 2, AGFT achieves the highest average performance across all four model configurations. Compared with the strongest baseline in each configuration, AGFT improves the average score by 2.95, 0.82, 2.04, and 1.86 points on Qwen2.5-3B, Qwen2.5-7B, Llama-3.2-3B, and Llama-2-7B, respectively, yielding an average improvement of 1.92 points across all configurations. These results suggest that AGFT maintains its performance advantage across different model families and fine-tuning settings.
Regarding TRACE, it is important to note that Replay and AGFT operate under different data access settings. Replay stores and reuses training data from previous tasks, whereas AGFT does not require access to any historical training samples. AGFT achieves better performance than Replay, even though the performance margin is small for the full fine-tuning models. This demonstrates that AGFT can effectively preserve previously learned knowledge without relying on storing or replaying historical task data, highlighting its practical advantage in continual learning scenarios where access to previous-task data is limited or prohibited.