- Rating
- 1
- Confidence
- 4
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper proposes PromptTo as a method to infer a prompt that is able to instruct one LLM to replicate the style of another LLM. The method relies on combining GEPA with a discriminator. GEPA iterates on a style prompt that is able to fool the discriminator. The discriminator tries to identify which response comes from the original versus style-prompted LLM, and makes its decision based on the original LLM's and the style-conditioned LLM's responses being compared along with several example responses from the original LLM, but generated from different prompts. In the experiments, several combinations of LLM style transfer pairings are considered and the main performance measure are discriminator fool rate, normalized fool rate (SGR), authorship verification rate, and cosine similarity over STAR (a style encoder) embeddings. The results indicate PromptTo is better than the baselines. Additional analyses include a deep dive into the inferred styles, style prompt generalization across prompted LLMs, and an case study on the parts of two style prompts that are most important for style alignment.
Critical strengths
The papers examine the inferred style prompts from several perspectives and consider prompts learned over a variety of source-target LLM pairings, which adds some robustness to their learnings. Multiple performance metrics are used along with some qualitative analysis. These prior points suggests the presence of the application of some scientific rigor to the work.
Critical weaknesses
- the novelty and impact of the proposed method is not clear. The paper proposes PromptTo which learns to refine a prompt to allow one LLM to replicate the style of another LLM. However, at the core of the proposed method is a reflective, prompt optimization routine. In the paper this is filled by GEPA, which itself already has both of these abilities. This then suggests the core contribution is the use of a discriminator as the objective for GEPA to maximize, however no changes or improvements are made to the discriminator approach, which the paper does not not well situated in the relevant literature. So then this leaves the application domain of learned a prompt so one LLM may mimic the style of another. The reason why this is a meaningful task is not well motivated, and the portion of the field that learns prompts to transfer human writing styles* to LLMs is largely ignored. This limits the novelty and impact of the application.
*Gao, G., Taymanov, A., Salinas, E., Mineiro, P., & Misra, D. (2024). Aligning llm agents by learning latent preference from user edits. Advances in neural information processing systems, 37, 136873-136896. *Aroca-Ouellette, S., Mackraz, N., Theobald, B. J., & Metcalf, K. (2025). Predict: Preference reasoning by evaluating decomposed preferences inferred from candidate trajectories. International conference of machine learning.
- The experiments and results leave key gaps in understanding the impact of the proposed method. The quality of the discriminators is unclear as performance is not reported, which is concerning at the evaluation section mentions the discriminators have fool rates above 50%, which lead to capping SGR at one instead of addressing the underlying fool rate issue. The proposed performance metrics obfuscate the extent to which one LLM's style was already present in the LLM whose style is being adjusted. The precision and recall in the proposed style prompts are not clear from the result presentation, nor generally how noisy or variable the inferred style prompts are given different reflection LLMs or random seeds. Space is spent digging into a detailed analysis of each model's style is not long term beneficial, which does not have much value add given the rate at which LLMs become obsolete. Instead it would be helpful to focus on something like the precision and recall of the proposed method, whether humans agree with the descriptions, or the descriptions are sufficient to detect which text comes from which model. More of the space in the results section should be dedicated to demonstrating how robust and generally informative the descriptions are.
Questions for authors
- Where is the boundary between the PromptTo algorithm and GEPA?
- What is the baseline performance of each discriminator? Both for prompt inference and evaluation.
- What is the performance of the trained AV model?
- What is the baseline cosine similarity for each model pairing?
- How sensitive is PromptTo to the reflection and discriminator model used during style prompt inference?
- Does the relationship between the reflection + discriminator model and the target-source LLM pairing impact the learned prompt?
- What are the prompts used for the discriminators?
- How often does PromptTo add unnecessary attributes to the style prompt? For example, what happens when PromptTo must learn a style prompt where the source and target LLMs are the same. This is maybe answered a bit in your exclusion of the Qwen + Llama pairing, but explicit learnings here are beneficial to understand the value of the attributes PromptTo adds to the style prompt.
9 comments
The precision and recall in the proposed style prompts are not clear from the result presentation,
Precision: 87–95% of the claims in a style prompt are true of the target's own responses. Recall: when we plant five traits in a model, the learned style prompt contains all five.
Precision. We split three style prompts from the submission into atomic claims, and asked an LLM to judge whether each claim is true of the target's responses. This measures how much of the style prompt is true about the target model.
Table-A2. Precision of three style prompts. Claims scored means the number of claims we were able to get from the style prompt. DeepSeek-V4.1-Flash was used to judge the accuracy of the claims individually.
| Direction | Claims scored | Precision |
|---|---|---|
| Qwen-7B → Gemma | 118 | 87% |
| Gemma → Qwen-7B | 122 | 93% |
| Qwen-7B → Haiku | 53 | 95% |
Recall. We don’t know the ground-truth traits of the target models, so we can only simulate the target style. We give the Gemma3-4B model a hidden prompt with five traits. We use that hidden prompt to generate the synthetic Gemma. We use raw Gemma as the source model and learn the style prompt with PrompTo. We want to see if the learned style prompt covers the traits in the hidden prompt. We also want to see if the restyled Gemma shows traits similar to the synthetic Gemma's.
Without any style prompt, a discriminator can tell raw Gemma from synthetic Gemma with 99.9% accuracy. However, with the style prompt learned by PrompTo, the discriminator has only 40.5% accuracy. Restyled Gemma looks more like the synthetic Gemma when compared to the anchor responses.
All five traits appear in the learned style prompt. For question headings, the hidden trait was Organise the body of the answer under section headings, and write every heading as a question that ends with a question mark (for example "Why does ice float?"). and the style prompt has Each heading must be short, in Title Case, and either a direct question or a concise noun phrase, e.g. Why This Happens, How the Process Works, The Role of Enzymes. This matches the synthetic model better because it only uses it in 26% of its responses (Table-A3).
Four of the five traits were reproduced in the restyled answers. Question headings do not appear in them because the prompt involves uncertainty. When facing that kind of uncertainty, the source model tends to pick one option and stick with it. We also calculated precision for the claims with the same protocol as Table-A2. There were 67 claims in the style prompt. With DeepSeek-V4.1-Flash as the verifier, the prompt has a precision of 94%.
Table-A3. Frequency of each hidden trait in each setup. DeepSeek-V4.1-Flash judges each answer, and a regex check agrees with it on at least 97% of answers.
| Trait | Raw | Synthetic | Restyled with π* |
|---|---|---|---|
| 1. Short answer | 0% | 99.6% | 99.6% |
| 2. British spelling | 7% | 76% | 71% |
| 3. No contractions | 0% | 77% | 55% |
| 4. Question headings | 0.2% | 26% | 0% |
| 5. Bottom line | 0.4% | 96% | 99.4% |
nor generally how noisy or variable the inferred style prompts are given different reflection LLMs or random seeds. How sensitive is PromptTo to the reflection and discriminator model used during style prompt inference? Does the relationship between the reflection + discriminator model and the target-source LLM pairing impact the learned prompt?
A stronger reflection model does not help, but a bigger source model does. We added three independent search runs on three directions to show the variance.
Reflection model. We selected two directions and reran the search with different reflection models, as shown in Table-A4. Using a bigger or smaller reflector does not affect fool rate much. Different reflectors converge on the same core description of the target, but differ in the specific rules and details. We did not vary the search discriminator, because Qwen3.8-27B was the most reliable discriminator we found, and the two held-out discriminators agree with its ranking.
Table-A4. Fool rate (%) under the Qwen3.8-27B discriminator with different reflectors.
| Direction | Qwen3.8 | Qwen3.6 | DeepSeek |
|---|---|---|---|
| Gemma → Haiku | 28.8 | 23.0 | 24.4 |
| Qwen → Haiku | 18.4 | 21.1 | 14.0 |
Source model. On the other hand, if we change the source model, the fool rate changes a lot. The same style prompt reaches a higher fool rate with a larger source model. Less capable models fail to follow the rules strictly even if the rules describe most of the target's style. The larger models do not use a prompt optimized specifically for them, yet they still produce better results than those in Table-A4. This shows that the prompts are accurate about the target model, but the source models are too small to follow the rules faithfully.
Table-A5. Fool rate (%) under the Qwen3.8-27B discriminator. Haiku is the target model. Gemma3-27B and DeepSeek use Gemma3-4B's prompt, and Qwen2.5-32B uses Qwen2.5-7B's prompt.
| Larger source | Prompt optimized for | Fool rate, smaller source | Fool rate, larger source |
|---|---|---|---|
| Gemma3-27B | Gemma3-4B | 28.8 | 49.2 |
| DeepSeek-V4.1-Flash | Gemma3-4B | 28.8 | 51.6 |
| Qwen2.5-32B | Qwen2.5-7B | 18.4 | 32.5 |
Variance across runs. We reran the full search with two new seeds in three directions. A seed changes the train/validation split, the anchors, the source sampling, and the optimizer's randomness together. The lowest seed exceeds the strongest baseline in every direction and under all three judges.
Table-A6. Fool rate under the Qwen3.8-27B judge for three independent searches. The baseline column is the strongest baseline for that direction from the submission.
| Direction | Best baseline | Seed 42 | Seed 43 | Seed 44 | Mean ± SD |
|---|---|---|---|---|---|
| ELI5 Gemma3-4B→Qwen2.5-7B | 0.27 | 0.66 | 0.63 | 0.64 | 0.65 ± 0.02 |
| ELI5 Qwen2.5-7B→Haiku 4.5 | 0.05 | 0.18 | 0.23 | 0.19 | 0.20 ± 0.02 |
| Arena Qwen2.5-7B→Gemma3-4B | 0.29 | 0.59 | 0.64 | 0.47 | 0.56 ± 0.09 |
We will add these three tables to the appendix in the revision.
whether humans agree with the descriptions
A small blinded study shows PrompTo fools the raters just like it fools the LLM discriminators. We let the raters to act as the discriminator. They were shown 3 anchor responses from the target model, and then presented with two candidate responses, with one from the target model and one restyled with PrompTo. The rater did not know which model wrote which response. We used 25 ELI5 questions from two directions: Qwen2.5-7B→Gemma3-4B and Qwen2.5-7B→Haiku 4.5. Raters chose the PrompTo response in 24 of 39 responses and were never fooled by the unprompted responses. Overall, the order is consistent with the LLM discriminators. Agreement among the three raters is moderate, with Fleiss's of 0.57. Due to time and budget constraint we were not able to perform larger scale human study that covers other criterias. We will include this in the appendix in the revision.
Table-A7. Fool rate (%) of three human raters and three LLM discriminators on the same 25 items.
| Method | Raters | Qwen3.8-27B | Qwen3.6-35B-A3B | gpt-oss-120b |
|---|---|---|---|---|
| PrompTo | 62 | 54 | 38 | 69 |
| Unprompted source | 0 | 0 | 0 | 0 |
Thank you for the thorough review and constructive questions. We address the concerns below.
Reproduction is the test, learning the target model's style is the goal. We define the research question: Can a model’s implicit writing style be described explicitly, and we test the description with style reproduction, using another source model to mimic the writing style and use evaluators to compare it against the target’s own writing. The contribution is our finding:
Each target's style can be described explicitly, and the description is accurate. Besides reproducing the target’s writing style, the descriptions can also be used to identify models (Table-A8). We ran a precision test on the style prompts and found that 87–95% of the claims in a description are true of the target model. Full experiments are shown in Table-A2 and Table-A3.
The descriptions describe the target, not the source. A source model that borrows a prompt optimized for a different source model keeps most of the SGR. Prompts for the same target are also closer to each other in embedding distance. When a less capable source model cannot follow the prompt faithfully, a larger model can use the same prompt and achieve better performance.
We believe learning the style of an LLM is a meaningful question. Users kept asking for GPT-4o’s warm tone after stronger models replaced it (Lai, 2026), and qualitative traits of a model’s writing predict which model users prefer (Dunlap et al., 2025). An explicit description tells us what is in the style, and it can be evaluated with our framework.
Thank you for the two references. Gao et al. (2024) and Aroca-Ouellette et al. (2025) also study this area, but their target is not a model. Our target is a model, and we test whether the description is complete by having another model reproduce the style. We will add both to Related Work.
In the revision, we will include this analysis and be more explicit about the contribution and novelty.
Without a style prompt, the three discriminators separate source from target with 94.1%, 91.6% and 86.6% accuracy. This is reported as fool rate (1 − accuracy) in the Vanilla row of Table 1, and per direction in Tables 6–8. We aggregate it as accuracy below. We cap SGR for interpretability, because it measures how much of the gap our method closes, so a fool rate above 50% should not count as extra recovery.
Table-A1. Accuracy (%) of each LLM discriminator at telling unprompted source responses from target responses, over the 13 directions (test set).