- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper investigates cross-model personalization, aiming to transfer user preferences learned by a small on-device language model to a larger server-side model without directly sharing the user's private training data.
Critical strengths
S1. The topic is interesting.
S2. The writing is easy to understand and follow.
S3. Experiments have some interesting insights.
Critical weaknesses
W1. The paper requires a group of training users, and the privacy of these users is not considered.
W2. Another potential limitation is that, it is unknow for the requirement of personalization overlap between training and unseen users. If the distribution various a lot, can the method still works?
W3. For the technical design, using a projection network with a soft prompt for personalization has been studied for a long time. Although the paper may have some new design, the overall framework seems “familiar with not too much surprise” to me.
W4. For the experiments, it is questionable whether, except for the writing style task, other tasks can indicate/need personalization.
Questions for authors
Please address the concerns in weaknesses.
2 comments
W4. For the experiments, it is questionable whether, except for the writing style task, other tasks can indicate/need personalization.
While the Amazon rating prediction task shows little need for personalization, as the task is to predict a rating from review text, such a task may still benefit from personalization. The MovieLens task requires much more personalized learning, as the task is to predict a rating given only a movie title (which means there can be different labels for the same input). Results are given below, showing that F1 performance drops substantially when personal information is removed:
| Accuracy | Macro-F1 | ||||
|---|---|---|---|---|---|
| Small | Large | Full | Global only | Full | Global only |
| Pythia-410M | Qwen3-14B | 0.3981 | 0.3618 | 0.2793 | 0.2121 |
| Pythia-410M | Qwen3-8B | 0.4114 | 0.0657 | 0.3540 | 0.0247 |
| Pythia-410M | Pythia-12b | 0.3823 | 0.3460 | 0.2617 | 0.1574 |
| GT Large | Pythia-12b | 0.4065 | 0.3565 | 0.3387 | 0.2050 |
| GT Large | Qwen3-8B | 0.4138 | 0.3619 | 0.3631 | 0.2338 |
| GT Large | Qwen3-14B | 0.4240 | 0.3663 | 0.3789 | 0.2544 |
In the Projected Qwen3-8B setting, Global only degenerated and only predicted “1” for all samples. These results are over our test set, not the full MovieLens-1M dataset. Note that for the GT Large Global Only setting, there is no pre-pending of zeroed out prompts, and these global prompts were learned across the full training population, meaning they represent the best that this method can possibly do without personalization, and we see that they fall short of both GT Large with personalization and Projected with personalization. These results, coupled with the results in the full paper, show that this personalized extension is beneficial when the task demands personalization, and does not adversely affect task performance when personalization is not required.
We thank the reviewer for their time and consideration.
W1. The paper requires a group of training users, and the privacy of these users is not considered.
We agree, and this is an area we highlight at the end of our conclusion for future work. While private federated learning could be applied to these users, that is beyond the scope of this work. In this work, we show that this architecture works in “ideal conditions”, and future work may consider how to further improve under additional constraints, such as private learning of the projector or global prompts. We will clarify that the training users do share their personal data with the server.
W2. Another potential limitation is that, it is unknow for the requirement of personalization overlap between training and unseen users. If the distribution various a lot, can the method still works?
We test on unseen users in each dataset, ranging from ~300 in MovieLens to ~6700 in AmazonReviews. These unseen users vary significantly, and show that the projector does generalize beyond simply covering the training users. We examine this in more detail by analyzing win rates on the Amazon review writing task for users with varying degrees of similarity to the training users. In the below table, we show win-rates for the Projected method against the GT-Large baseline for users that are within 1 standard deviation of the training-user distribution. 1-2 standard deviations, 2-3 deviations, and 3+ deviations (where distance is computed on the learned small-model soft-prompts).
And comparing the Projected method against the No-Personalization baseline
These results show that performance degrades as prompts are further from the training mean when compared to the GT-Large baseline, but that performance is steady when compared to the No-Personalization baseline.
W3. For the technical design, using a projection network with a soft prompt for personalization has been studied for a long time. Although the paper may have some new design, the overall framework seems “familiar with not too much surprise” to me.
We thank the reviewer for their comment, and we note that we are the first to show this approach generalizes across model scales and families to unseen users, as demonstrated in the “write in my voice” and product recommendation tasks, and we have rigorously evaluated multiple solutions to this problem (e.g., direct mapping, backprop through a large model, global prompts vs. personal prompts, and comparison to prompting baselines). However, we will modify the motivation and conclusion to clarify that this work builds on foundations established in prior work.
Due to character constraints, we continue our response in a separate comment.