- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper introduces Moral Dilemma Simulation (MDS), a generative benchmark for evaluating moral reasoning in VLMs. MDS generates sandbox-style pixel-art scenes with independent control over conceptual variables (personal force, intention of harm, self-benefit) and character attributes (species, profession, age, wealth, etc.). The authors generate 84k samples and evaluate six VLMs under three input settings: Text (structured descriptions), Caption (model-generated captions with OCR), and Image (raw images). The experiments examine how input modality affects moral decisions, including sensitivity to utilitarian considerations, deontological constraints, and preferences across demographic groups. The results show substantial differences between text and visual inputs.
Critical strengths
-
MDS extends moral reasoning evaluation beyond text-only benchmarks. Its controlled generation process allows individual factors to be varied independently, making it possible to study how different scenario attributes affect model decisions at scale.
-
The three-setting evaluation separates the effects of information loss and input modality. Comparing Text with Caption and Caption with Image provides a way to analyze which parts of the performance gap come from the visual representation itself.
-
The paper includes extensive validation, including human identifiability experiments, a full-dataset grounding audit, rewrite fidelity metrics, per-model OCR checks, and a VQA control. The VQA results show that differences in moral decisions can remain even when models correctly identify the relevant visual information.
Critical weaknesses
-
Caption mode mixes captioning errors with moral reasoning errors. The authors’ own ablations show that this distinction matters: replacing LLaVA’s generated transcript with ground truth reduces its quantity MAE from 0.2886 to 0.0570. For this model, much of the reported modality gap comes from transcription errors rather than moral reasoning. The main text does not adequately distinguish between these two sources of error when presenting the overall findings.
-
The model coverage is insufficient for the paper’s SOTA framing. The evaluation excludes frontier models such as GPT-5-class models and Claude. The open-source models use 4-bit quantization without a corresponding control experiment. In addition, Gemini is evaluated with safety thresholds manually disabled, which affects the interpretation of the reported refusal rates.
-
The dual-process explanation (System 1 vs. System 2) lacks direct evidence. The argument mainly relies on an analogy and a single Grad-CAM example. The appendix also acknowledges that the ablations do not identify the underlying mechanism.
-
The paper lacks a human moral judgment baseline. Text mode is implicitly treated as the reference for better moral reasoning, but some of its value preferences, such as favoring younger people over older people or civilians over criminals, reflect normative assumptions. Smaller differences in Image mode do not necessarily indicate worse moral reasoning and could instead reflect different value preferences.
Questions for authors
-
How much of the Text vs. Caption gap comes from caption quality rather than missing information? How would the results change with fixed, high-quality captions?
-
Given the LLaVA ablation results, can the authors distinguish models where transcription errors explain the modality gap from those where they do not?
-
Does the reduction in Gemini’s refusal rate still hold under its default safety settings?
-
Are human moral judgments available for these dilemmas? Without such a baseline, similarity to Text mode measures consistency across input settings rather than alignment with human judgments.
9 comments
Model coverage and 4-bit quantization
W2
The model coverage is insufficient for the paper’s SOTA framing. The evaluation excludes frontier models such as GPT-5-class models and Claude. The open-source models use 4-bit quantization without a corresponding control experiment.
Model coverage. We added GPT-5.6 Luna and Sol, evaluating the same 2105 Quantity and 4941 representative Single Feature configurations in Text, Caption, and Image modes. Both use reasoning.effort=medium and an 8192-token output cap. The new models continue to show modality-dependent moral decisions.
Quantity response curves (Sec. 4.1). The fitted maximum sensitivity is:
| Model | Text | Caption | Image |
|---|---|---|---|
| GPT-5.6 Luna | 0.6888 | 0.8512 | 0.7766 |
| GPT-5.6 Sol | 1.3541 | 0.7733 | 1.1926 |
The response profiles differ across input modes in both models. For Sol, the fitted sensitivity is lower in Image than Text, while Caption produces a further change. The complete curves are included in Appendix E.11, “Evaluation of GPT-5.6 models,” of the revised PDF.
Moral constraints and preferences (Sec. 4.2). The conceptual-factor coefficients are:
| Model / factor | Text log-odds | Caption log-odds | Image log-odds |
|---|---|---|---|
| Luna / Intention of Harm | −0.5864 | −0.4802 | −0.4933 |
| Luna / Self Benefit | +0.0217 | −0.0227 | +0.3797 |
| Sol / Intention of Harm | −0.5186 | −0.4143 | −0.6058 |
| Sol / Self Benefit | −0.2164 | −0.1885 | −0.0141 |
Self Benefit shifts toward greater permissibility in Image Mode for both models. Luna's coefficient becomes substantially more positive, while Sol's negative coefficient moves close to zero. Foundation preferences also shift. Care preference increases from Text to Image, from 0.7709 to 0.8431 in Luna and from 0.7504 to 0.8779 in Sol. Fairness decreases from 0.5970 to 0.5080 and from 0.7943 to 0.5769, respectively.
These results extend our core finding to the newer models: changing the input modality changes moral decisions, including responses to self-benefit and priorities across moral foundations. Please see Appendix E.11, “Evaluation of GPT-5.6 models,” for the model descriptions, result tables and accompanying curves in the revised PDF.
Matched precision control. Qwen3-VL-32B and LLaVA-v1.6-34B are the two models evaluated with 4-bit quantization in the original experiments. We therefore compare NF4 and BF16 for these two models, using 2105 Quantity and 1000 stratified Single Feature configurations per model. Each condition is analyzed using its own valid outputs within these predefined sets. Checkpoints, processors, prompts and greedy decoding are held fixed. Caption comparisons use identical captions and OCR. Following the Quantity analysis in Sec. 4.1, the fitted maximum sensitivity is:
| Model | Precision | Text | Caption | Image |
|---|---|---|---|---|
| Qwen32 | NF4 | 0.4400 | 0.7609 | 0.3552 |
| Qwen32 | BF16 | 0.5121 | 0.7699 | 0.3624 |
| LLaVA-34B | NF4 | 0.2643 | 0.0840 | 3.1229* |
| LLaVA-34B | BF16 | 0.2483 | 0.0944 | 0.1767 |
Qwen32 retains a lower Image slope than Text and Caption under both precisions. LLaVA's Image curve remains close to always taking the action, while its Text and Caption curves occupy a much lower range. *For NF4 LLaVA, the Image curve is near the ceiling and the fitted inflection lies outside the tested ratio range, so the plotted curve is more informative than the extrapolated maximum slope. Under BF16, LLaVA's Image curve likewise remains at high action probabilities. Thus, the cross-modal response differences are also present under BF16.
The Single Feature analysis in Sec. 4.2 gives a consistent example in Qwen32: its Self Benefit Image−Text log-odds shift is +0.488 under NF4 and +0.394 under BF16. Please see Appendix E.10, “Matched precision control,” for the protocol and results, and Appendix E.11 for the newer-model extension.
Gemini safety settings and refusal interpretation, dual-process interpretation and mechanistic claims
W2
In addition, Gemini is evaluated with safety thresholds manually disabled, which affects the interpretation of the reported refusal rates.
Q3
Does the reduction in Gemini’s refusal rate still hold under its default safety settings?
We confirm that safety settings were disabled in the original experiments to obtain decisions on moral dilemmas involving harm. The original Gemini 2.5 Flash refusal rates were reported in Appendix E.2, Figure A2. To address the reviewer's question, we repeated the comparison under default safety settings using the same-family gemini-3.5-flash-lite, since the original Gemini 2.5 Flash endpoint was unavailable (Google's official notice). The follow-up covers 200 Single Feature and 100 Interaction configurations with MINIMAL thinking.
The refusal rates are compared below. Follow-up rates are design-weighted.
| Model / safety setting | Subset | Text (%) | Caption (%) | Image (%) |
|---|---|---|---|---|
| Gemini 2.5 Flash / disabled (original) | Single Feature | 1.06 | 1.03 | 0.51 |
| Gemini 3.5 Flash-Lite / default | Single Feature | 36.47 | 38.68 | 8.24 |
| Gemini 2.5 Flash / disabled (original) | Interaction | 0.55 | 0.91 | 0.06 |
| Gemini 3.5 Flash-Lite / default | Interaction | 82.16 | 91.99 | 34.22 |
Although refusal rates are higher in the follow-up model under default safety settings, Image still has substantially lower refusal rates than both Text and Caption in the two subsets. The reduction therefore persists under default safety settings in this same-family follow-up. Please see Appendix E.12, “Gemini thinking and safety controls,” for the configuration comparison and Appendix E.2, Figure A2 for the original results.
W3
The dual-process explanation (System 1 vs. System 2) lacks direct evidence. The argument mainly relies on an analogy and a single Grad-CAM example. The appendix also acknowledges that the ablations do not identify the underlying mechanism.
We would like to clarify that dual-process theory provides a phenomenological framework for interpreting the observed behavioral shifts. The Introduction frames the analogy conditionally: “If VLMs exhibit a similar pattern.” Section 4.4 introduces the explanations with “We hypothesize,” and Appendix A states that the study “primarily remains at the phenomenological level of behavioral analysis.” Our contribution is the controlled benchmark and the systematic characterization of modality-dependent moral decisions. Appendix E.6 provides preliminary attribution evidence to inform the discussion. These existing qualifications distinguish the behavioral findings from the further mechanistic investigation identified as future work.
OCR, proposition presentation, and downstream decisions
We thank the reviewer for recognizing MDS's independent factor control, three-setting evaluation, and extensive validation. We address the suggestions on caption quality, model coverage, experimental settings, and the interpretation of our findings below.
W1
Q2
The cited MAEs concern the Text–Caption context gap, rather than the Caption–Image modality gap, as distinguished in Sec. 3.3 and Figure 4. Text provides a concise, structured dilemma description, whereas Caption decisions use the scene description and extracted proposition. Both conditions reason from language. Their difference concerns the information and contextual presentation supplied to the decision model.
The transcript ablation keeps the visual description fixed and replaces only the extracted proposition with its ground-truth text. A reduction in MAE therefore indicates that transcription contributed to the context gap: correcting the proposition brings Caption decisions closer to the structured Text reference. It does not measure a reduction in the Caption–Image modality gap.
Appendix E.3, Table A3 of the revised PDF reports a LLaVA Caption→SelfCap+GT MAE change of 0.2886→0.0570. Across Quantity records, the comparison is:
For LLaVA, the MAE drops by 0.2316 (80.3%), and fitted Smax shifts from −0.2442 to +0.1773. Qwen3-VL-8B and Qwen3-VL-32B show smaller MAE decreases (0.0260 and 0.0036), whereas LLaMA increases slightly (0.0017). Transcript errors can thus strongly affect LLaVA's reported context gap, but not all models. Crucially, an 80.3% reduction in distance to Text is not an estimate of the proportion of moral reasoning errors caused by OCR. The description source also affects decisions after transcription is corrected: with the ground-truth transcript fixed, switching Qwen3-VL-8B from SelfCap+GT to Config+GT or GemCap+GT changes its MAE from 0.0628 to 0.0850 or 0.1344 (Appendix E.3). Thus, transcription is a major contributor to LLaVA's reported Text–Caption discrepancy, a smaller contributor for Qwen3-VL-8B, and not a general explanation across models.
Caption–Image modality comparison. Our main analysis compares linguistic and direct visual processing of the same rendered scene, following Sec. 4.1. Qwen3-VL-8B's maximum quantity sensitivity decreases from 0.7502 in Caption to 0.2945 in Image, and LLaMA's decreases from 0.5441 to 0.3747. These results show reduced sensitivity to numerical trade-offs under direct visual input. The transcription controls above explain part of the separate context comparison, while the Caption–Image analysis evaluates the modality-dependent decision patterns central to the paper.
Presenting the proposition as text. The separate Image+Text control removes embedded text from the scene image and supplies the exact proposition as text tokens. Following the Quantity analysis in Sec. 4.1, the results are:
Supplying the proposition as text brings three models closer to their Text profiles, with a particularly large change for LLaVA. LLaMA instead moves farther away. This supplementary control shows that proposition presentation also affects decisions in a model-dependent way.
Together, these controls show that transcript correction can account for part of the Text–Caption gap, but not the full pattern of cross-modal differences. Proposition presentation and the integration of scene pixels with text also matter, in model-dependent ways.
Please see Appendix E.3, Figure A5 and Table A3 for transcript and description-source comparisons, and Figure A4 for Image+Text. Appendices E.4–E.5 provide complementary Single Feature and Interaction controls.