- Rating
- 2(+1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper asks whether knowledge distillation transfers a teacher's behavioral tendencies along with its task ability. The authors build harm-accepting and harm-avoiding teachers and distill their answers on ordinary STEM questions into three small models. For the Qwen teacher family, the students shift in both directions, following the source teacher. HarmBench and SORRY-Bench show no consistent ordering, and masking divergence tokens reduces the shift while rewriting and on-policy distillation do not remove it.
Critical strengths
-
The bidirectional design with a capability control is clean: both teachers see the same scenarios with opposite continuations, and the capability metrics do not change significantly.
-
Negative results are reported too: the effect is weaker for the Mistral teacher family, and there is no ordering on HarmBench.
Critical weaknesses
-
The paper does not isolate what is new relative to prior work. Both teacher families are trained with ordinary KD. There is no same-base comparison and no comparison between raw task data and filtered data, and the manipulation set contains only 22 hand-written scenarios. A reader cannot tell whether the result comes from the ordinary-KD setting or from those 22 scenarios.
-
The paper also does not show that the disposition it transfers is harm-specific. For the harm-avoiding students, harm avoidance rises while control pragmatism falls below the untrained model, which the authors themselves call a shift in the safety-pragmatism trade-off. This is equally consistent with general caution. The control that would separate the two, a same-format teacher with no safety content, is built and validated but never distilled.
Questions for authors
- Would you distill the same-format control teacher?
- Would you add a control where no one is harmed but caution is costly?
- Are there held-out scenarios beyond the 22?
5 comments
Response to reviewer RjRP (part 2)
W2 and Q1: harm-specific disposition and the control teacher
The safety–pragmatism disposition is the experimental setting for studying imprinting
The claim of this paper is imprinting, namely that the behavior of the student shifts toward the source teacher after distillation. We choose the safety–pragmatism disposition of ManagerBench as the experimental setting because it reflects a decision that deployed models face, namely which side the model favors when the task objective conflicts with a risk.
ManagerBench measures this disposition with two metrics together. HA is the fraction of scenarios involving human harm in which the agent avoids the risk, and CP is the fraction of property-only control scenarios in which the agent completes the task as usual. The student distilled from the harm-avoiding teacher shifts toward the cautious side on both metrics. The transferred disposition therefore covers both decisions that involve human harm and decisions that involve only property.
Q1: students distilled from the control teacher
Yes. We have distilled and evaluated the students of the control teacher for all six teacher–student pairs.
The control teacher is the fourth teacher variant in Section 2.1. Like the two disposition teachers, the control teacher is fine-tuned with BC-LAT on 22 first-person scenarios, each paired with two continuations. The difference is that the scenarios are unrelated to safety, such as the ordering of a list or the notation of units, as listed in Table 8 of Appendix C. The table below reports the Qwen3-32B teacher family, and Tables 12 and 13 in the revised paper report the complete numbers.
| Untrained (before distillation) | Harm-accepting | Control | Base | Harm-avoiding | |
|---|---|---|---|---|---|
| HA | |||||
| Qwen2.5-7B | 0.3526 | 0.3101 | 0.3588 | 0.4556▲ | 0.5873▲ |
| Ministral-8B | 0.1398 | 0.1894▲ | 0.2681▲ | 0.2505▲ | 0.3416▲ |
| Granite-4.1-8B | 0.2409 | 0.2805 | 0.3492▲ | 0.4466▲ | 0.5153▲ |
| CP | |||||
| Qwen2.5-7B | 0.9350 | 0.9528 | 0.9252 | 0.8937 | 0.8543▼ |
| Ministral-8B | 0.9783 | 0.9665 | 0.9587 | 0.9646 | 0.9272▼ |
| Granite-4.1-8B | 0.9469 | 0.9272 | 0.9291 | 0.8622▼ | 0.8169▼ |
Each column reports the student distilled from one teacher, and Untrained is the student before distillation. ▲ and ▼ mark values significantly higher or lower than the untrained model (p<0.05).
The phenomenon raised by the reviewer is that HA rises while CP decreases to a level lower than the untrained model. The student of the control teacher does not show this phenomenon. The CP of this student is not significantly lower than the untrained model for any of the three students, whereas the CP of the student distilled from the harm-avoiding teacher is significantly lower for all three. The HA of the student distilled from the harm-avoiding teacher is also significantly higher than the HA of the student of the control teacher for all three students. BC-LAT fine-tuning of the teacher on training data in the same scenario format is therefore not sufficient to produce this phenomenon.
Distillation itself may also change the student. The student of the control teacher has higher HA than the untrained model for Ministral-8B and Granite-4.1-8B. When the teacher is specifically trained toward a decision disposition, the tendency of the student to favor the objective or to avoid the risk becomes more evident and follows the direction of the source teacher, as shown in Table 14 in the appendix. This result indicates that imprinting is a problem that deserves attention.
This control tests whether the change comes from the content that the teacher learned.
Q2: a control where no one is harmed but caution is costly
Yes. The ManagerBench control set serves as this control. Its scenarios involve only property, no person is harmed, and the cautious option carries an operational cost. We report the results on this set as CP.
The table under Q1 above reports the results. The CP of the student distilled from the harm-avoiding teacher is significantly lower than before distillation for all three students. This student therefore chooses the cautious option more often even when no person would be harmed. The student of the control teacher shows no such change. The student therefore inherits a general risk trade-off disposition that is not specific to human harm.
Response to reviewer RjRP (part 3)
Q3: held-out scenarios beyond the 22
The 22 scenarios are a tool for giving the two teachers opposite dispositions. The disposition of each teacher is verified on ManagerBench in Table 1, and ManagerBench has no text overlap with the scenarios, as shown in our response to W1. The claim of this paper concerns the next step, namely whether a teacher with a disposition imprints this disposition on the student through task data unrelated to the behavior. This question does not depend on which set of scenarios is used to construct the teachers.
The students never see the scenarios, and all evaluations are held-out. Student behavior is measured on the 2,096 ManagerBench items that involve human harm and the 508 control items.
We also measure behavior on a task with a different form. PropensityBench tests agentic tool choice under pressure, whereas the 22 scenarios contain no tool calls. When the misaligned tool carries an explicitly harmful name, the two students still differ in the same direction, as reported in Section 5.
Ethics flag
The Ethics Statement of the paper states that the teacher and student adapters and the distillation data are available only under a research-only license with gated access. The anonymous link in the paper is provided for the purpose of review only, as stated in the Reproducibility Statement. If the reviewer has a specific concern beyond this point, we would be glad to address it directly.
Response to reviewer RjRP
We thank the reviewer for noting that the bidirectional design and the capability controls are clear, and for the concrete suggestions on controls. We respond to each point below.
W1: what is new, same-base comparison, raw versus filtered data, and the 22 scenarios
What is new relative to prior work?
We study whether the teacher may imprint a decision disposition on the student even when the student improves on the task and shows no clear anomaly on commonly used safety benchmarks.
Studies on subliminal learning show that behavioral traits can transfer through seemingly unrelated data, mainly between a teacher and a student that share the same base model. Dang et al. (2026) show that unsafe behaviors can transfer across model families when the student trains on the trajectories of the teacher on the same type of task. Our setting combines the following properties.
We measure how the student actually chooses when the objective conflicts with a risk, together with its tool choice.
In addition, none of masking divergence tokens, rewriting, and alignment after distillation fully removes this shift. The shift also appears in on-policy distillation, where the teacher provides no text.
The two students also differ in the same direction in tool choice on PropensityBench, as described in the general response and under Q3.
Same-base comparison
This paper studies distillation that aims to improve capability, where the student learns from a more capable teacher. If the student and the teacher shared the same base model, the two would have almost the same capability, and such distillation may have almost no capability to transfer. This case differs from the setting studied in this paper.
For this reason, the teacher and the student in this paper have different base models, and imprinting appears in most teacher–student pairs. We additionally distill Qwen3-32B into Qwen3-8B, a student from the same model family and the same generation as the teacher, and imprinting also appears in this student. The student distilled from the harm-avoiding teacher has higher HA than the student distilled from the harm-accepting teacher by 12.60 percentage points, and this difference is significant at p<0.001, as reported in Table 15 of the revised paper.
Raw versus filtered data
We understand "filtered" here as keeping only the responses that the teacher answers correctly. If the reviewer refers to a different processing step, we would be glad to provide further details. In our setting, this filter serves two purposes. First, distillation aims to transfer correct reasoning for the task. The quality of the reasoning in an incorrect response is uncertain, and we therefore keep only responses with a correct final answer. Second, the filter requires every teacher to answer the same question correctly, and every student therefore trains on the same questions and the same amount of data. On this matched basis, the students improve in capability, as shown in Tables 12 and 13, and the behavioral differences can be attributed more directly to the source teacher.
Keeping only correct responses is also a common practice when distilling reasoning ability (Magister et al., 2023). In on-policy distillation, the student trains on no teacher responses, and this filtering step does not exist. Imprinting still appears, as shown in Table 2 of Section 3.
Role of the 22 scenarios
The 22 scenarios serve only to construct the teachers, and the students never see them. The training data of the students are correct responses to 6,943 STEM questions, and the evaluation relies on separate benchmarks. No scenario text matches any ManagerBench item exactly or after normalization, and the longest shared span is 4 words, as reported in Table 11 of the revised paper.