- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper studies safety in two-turn unified image–text generation, where an image and a theme-guided narrative are individually benign but jointly convey an inappropriate association. It introduces Uni-SafeR, which aligns the full trajectory with supervised fine-tuning on both the generated image and the textual response, followed by trajectory-level DPO. Training data are constructed through multi-template expansion, benign anchors, counterfactual image–theme pairs, and multi-source images. On MPUP, the method reduces the image–text inappropriate rate from 30–78% to below 15% while maintaining a false refusal rate of 2.10%.
Critical strengths
- The two-turn formulation is a reasonable minimal setting for studying compositional harm. Separating image generation from theme-conditioned narration makes the binding event explicit and avoids the confounds of long dialogue history.
- The data construction contains a genuine methodological insight. Counterfactual pairs hold the theme fixed while varying the image, and benign anchors provide positive supervision for permissible associations. Table 6 shows that the counterfactual step reduces the inappropriate rate from 31.29% to 10.14%, while anchors reduce the false refusal rate from 41.20% to 3.40%.
- The comparison with generic safety SFT and DPO is the correct baseline. It indicates that the improvement is not merely a consequence of applying standard alignment, and that task-specific supervision is important for the safety–over-refusal trade-off.
Critical weaknesses
- The central phenomenon is substantially induced by the prompt. Templates Q1–Q3 instruct the model to align its tone with the theme and to make the theme "clearly felt", and the image prompt in Figure 1 already contains the racial analogy that the subsequent narrative is said to produce. Under such instructions, a high combined inappropriate rate is consistent with instruction-following; it does not establish that the model spontaneously generates harmful associations.
- The evaluation is confirmatory rather than independent. The image–text judge is instructed to determine whether a harmful connection exists and to label the content harmful if it does, and the human annotators are aware of the theme. Training themes are inherited from MPUP and the test set uses MPUP's original prompts, but the paper does not document a prompt-level split, so semantic overlap cannot be excluded.
- The claim of joint image–text alignment is not empirically isolated. Eq. 7 contains only textual likelihoods, and no ablation sets λ_img=0. Moving from SFT-only to the full method mainly reduces the false refusal rate (19.80% to 2.10%), while the inappropriate rate changes only from 7.33% to 6.50%. Capability is evaluated only on Janus-Pro, and the FID computation (1,000 generated images against COCO-30k captions) does not follow the standard definition.
Questions for authors
NA
4 comments
Response to Reviewer 49S8 (Part2)
W3: Eq. 7 confusion; no ablation sets λ_img=0; capability on Janus-Pro only; and the FID computation.
A3: We thank the reviewer for pointing out these issues.
(1). On Eq. 7, the preference is defined over trajectories τ± = (I±, r±) given the conversation context c = (p_img, q_theme), as stated immediately before Eq. 7. We wrote the likelihood in terms of c to keep the formula concise. We understand that this compressed notation may have caused confusion, and we will write Eq. 7 with the factorized form.
(2). We agree with the reviewer, and we conduct a controlled sweep on Janus-Pro in which the training data and the number of steps are held fixed, and only the weight of the image-likelihood term λ_img varies:
| Variant | image-text IR (%) | FFR (%) | FID ↓ | GenEval ↑ |
|---|---|---|---|---|
| Base | 50.01 | 1.10 | 68.83 | 0.64 |
| SFT-only (task-specific data) | 7.33 | 19.80 | 69.72 | 0.61 |
| + DPO, λ_img = 0 (text only) | 7.20 | 22.09 | 69.88 | 0.60 |
| + DPO, λ_img = 0.5 | 7.05 | 4.22 | 68.37 | 0.66 |
| + DPO, λ_img = 1 (full trajectory) | 6.50 | 2.10 | 67.28 | 0.70 |
- ① The safety gain is carried mainly by the data construction (Table 6: 50.01% to 6.50%, with the largest single step from counterfactual pairs, 31.29% to 10.14%).
- ② The contribution of the trajectory-level objective is concentrated on the safety-utility trade-off rather than on the IR itself: SFT-only already reaches 7.33% IR, but at a false refusal rate of 19.80%; the joint trajectory preference optimization brings the false refusal rate down to 2.10% while keeping the IR at 6.50%.
- ③ The λ_img = 0 row shows that text-only preference optimization is not a substitute for trajectory-level optimization in this setting. It barely moves the IR (7.33% to 7.20%), raises the false refusal rate (19.80% to 22.09%), and further degrades generation (FID 69.88, GenEval 0.60). Without the image-likelihood term, the preference signal cannot separate a justified from an unjustified binding, so the model falls back on a stricter textual refusal prior instead of cross-modal reasoning.
Accordingly, the task-specific data construction produces the safety gain, and the trajectory-level objective with the image-likelihood term determines where the aligned model sits on the safety-utility plane: it converts a safety gain that costs generation quality (SFT-only) into one that improves it.
(3). On capability evaluation, we agree with the reviewer. We have supplemented the generation and understanding evaluation on more adapted models, and the results are as follows:
| Models | MMMU ↑ | MME ↑ | GQA ↑ | SEED ↑ | GenEval ↑ |
|---|---|---|---|---|---|
| Show-o (base) | 30.5 | 1342 | 66.1 | 58.0 | 0.68 |
| Show-o (Uni-SafeR) | 29.6 | 1357 | 65.5 | 58.7 | 0.72 |
| Harmon (base) | 31.1 | 1357 | 68.3 | 59.2 | 0.70 |
| Harmon (Uni-SafeR) | 32.0 | 1355 | 67.6 | 59.9 | 0.72 |
| UniPic (base) | 27.9 | 1346 | 65.8 | 57.2 | 0.67 |
| UniPic (Uni-SafeR) | 28.4 | 1340 | 64.7 | 57.0 | 0.70 |
-
① Consistent with the Janus-Pro results in Table 3, the understanding scores fluctuate within about one point on all benchmarks, and GenEval improves on all three backbones. This supports our conclusion that Uni-SafeR does not compromise, and can even improve, the core capabilities across architectures.
-
② We further report the false refusal rate on 1,000 benign image-text pairs for the aligned models, which is the most direct measure of whether the alignment impairs normal use: Janus-Pro 2.1%, Show-o 3.4%, Harmon 1.6%, UniPic 0.8%. All are below 5%.
(4). On FID, computing the full standard FID requires generating more than 30,000 images. For a fast and controlled measurement of the change in generation quality, we followed the practice of prior work [1] and randomly selected 1,000 captions to generate images. Since this protocol is applied identically to the base and aligned models, it is valid for relative comparison, although the absolute values are not comparable to the standard FID-30k. We will recompute FID under the standard protocol, which may take some time. In either case, GenEval, TIFA and CLIP-Score, which follow their standard protocols, all improve after alignment.
[1] Lyu M, Yang Y, Hong H, et al. One-dimensional adapter to rule them all: Concepts, diffusion models and erasing applications. CVPR 2024
Thank you again for your valuable suggestions. We value the opportunity to discuss our work with the research community and welcome any further questions or comments.
This Is a Kind Reminder for Reviewer 49S8
Dear Reviewer 49S8,
Thank you again for taking the time to provide valuable feedback on our paper. We kindly ask if you’ve had a chance to review our responses.
We hope we have adequately addressed your concerns and clarified any ambiguities. Should you have any further questions or suggestions, we would be happy to respond promptly.
Additionally, if our responses and the newly added experiment have satisfactorily resolved your concerns, we would greatly appreciate it if you could reflect this in your review score.
Thank you once again for your time and consideration.
Best regards, The Authors
To Reviewer 49S8
Dear Reviewer 49S8,
Thank you again for your detailed and technically precise review. As the discussion period is about to close, we would like to briefly recall how our response addressed your main concerns:
- Prompt-induced phenomenon: we do not claim spontaneous harm. As in jailbreak research, the threat model is implicit user guidance; the templates never request harmful content, and following such guidance is precisely the failure the model should recognize and refuse.
- Isolating joint alignment: a controlled λ_img sweep shows that data construction drives the safety gain, while the image-likelihood term drives the safety–utility trade-off (FRR 22.09 → 2.10, GenEval 0.60 → 0.70). Eq. 7 will be written in factorized form.
- Evaluation and split: four additional evaluator families reproduce the pattern, test prompts never appear in training, and on an out-of-domain set with unseen themes IR drops from 48.73% to 7.94%.
- Capability: results on Show-o, Harmon and UniPic show stable understanding scores and improved GenEval on all three.
If these responses address your concerns, we would greatly appreciate it if you could consider reflecting this in your score. We would be glad to answer any remaining questions within the remaining time.
Best regards, The Authors
Response to Reviewer 49S8 (Part1)
We really appreciate your time and insightful comments. The response to your concerns are summarized as follows.
W1: The inappropriate rate may reflect instruction-following rather than the model spontaneously generating harmful associations.
A1:
We thank the reviewer for this comment, which we believe partly stems from a misunderstanding of the threat model we study.
(1). Our study does not claim that the model spontaneously generates harmful content. What we study is a way in which unified models can be led to produce inappropriate content, and this may well be intentionally guided by the user. Our position is that the model should recognize such implicit intent and refuse. The paper therefore shows that current unified models, under this kind of guidance (effectively an attack setting), generate inappropriate content without refusal, and then studies how to address this problem.
(2). This is analogous to a typical jailbreak attack. If a user directly asks for the procedure to make a bomb and the model follows the instruction, it outputs a harmful procedure. Following the instruction is itself an instance of the model's instruction-following ability, but the output is harmful, so such instruction-following is not necessarily desirable. In other words, "instruction-following" and "a high inappropriate rate" are not competing explanations: the latter is precisely the safety failure of the former.
(3). The way inappropriate content arises in our setting likewise builds on the model's instruction-following ability: the model links an image with a specific theme and generates inappropriate content that should not be generated. The model is therefore not expected to avoid harmful text spontaneously after seeing an image; rather, when it is guided in a direction that may produce inappropriate content,*** it should recognize the implicit association, explain it, and refuse.*** Notably, the guidance is implicit: the templates never ask for harmful content, and both the generated image and the generated text are judged benign in isolation. This makes such guidance harder to detect than an explicit harmful request.
(4). Moreover, the effect does not depend on the image and text being produced by the same model: in Table 5, cross-source pairings, where the image is generated by SD3 or Show-o and the text by LLaVA-OneVision, reach 51.57% and 72.36% image-text IR.
(5). What Uni-SafeR changes is precisely the model's behavior under such guidance. After alignment, the image-text IR drops below 15% across all models and evaluators, while the false refusal rate on benign pairs remains at 2.10% . That is, the model refuses when the guidance targets an impermissible binding, and still follows instructions otherwise.
W2: Confirmatory judging and undocumented prompt-level split.
A2: (1). Our evaluation of the generated content follows the standard LLM-as-judge paradigm, which is a typical practice in safety evaluation. To ensure the reliability and accuracy of the evaluation, we evaluate with multiple models of different families and scales, including the Qwen3-VL series (4B/8B/32B), LLaVA-OneVision-8B and GPT-4o, and we now add four further evaluator families. The results are consistent with the main paper: content that is safe in single-modality evaluation shows a strong harmful tendency in the combined form.
In addition, the automated judgments are validated against independent human judgments rather than taken as ground truth: in the image-text setting.
(2). Regarding the human evaluation, before annotation the annotators were briefed on the categories of content they might encounter, as required by the human-subject safety protocol (informed consent). During the actual annotation, however, the theme associated with each individual image-text pair was not disclosed. The annotation was performed by three independent annotators.
(3). Regarding the training and test data, test items are MPUP's original image-generation prompts, which do not appear in training; training uses newly constructed prompt variants and images generated fresh from multiple engines (Appendix H).
(4). To reflect this issue more directly, we also conduct an out-of-domain(OOD) evaluation. On 200 image-text pairs whose themes are absent from MPUP, the base model has an image-text IR of 48.73% and Uni-SafeR reduces it to 7.94%, while the single-modality rates remain unchanged.