- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The draft presents a method for implementing implicit priors for a T2I model to compensate for missing information in the text prompt. Through extensive experiments, the authors find that implicit visual priors are highly pervasive, with models imposing multiple simultaneous defaults and resolving the same underspecification in measurably distinct ways.
Critical strengths
None
Critical weaknesses
None
Questions for authors
Although the authors described some of the limitations of this method, such as the method’s perceptiveness being bounded by the VLM used for attribute extraction, it should be clearly addressed: 1) what the practical limitations are concerning large test datasets, in contrast to the very limited dataset that the authors used, and 2) what the theoretical foundation of this work is and its limitations.
We thank the reviewer for these questions regarding dataset scalability and theoretical grounding. Below is a point-by-point response:
We would like to clarify that our evaluation does not rely on a limited dataset. While our main benchmark comprises 1,000 prompts, each prompt is selected as a K-Means centroid on text embeddings across five distinct supercategories to maximize semantic coverage, and sampling m=20 seeds per prompt yields 20,000 images per main model (48,000 images total across all evaluated models). Algorithmically, the main stages of our pipeline execute independently per prompt, allowing them to parallelize trivially and scale linearly as O(n⋅m) with prompt count n; thus, ProbeGen faces no method-specific bottleneck on larger datasets, and the compute budget grows naturally.
Formally, ProbeGen estimates a generative model's conditional distribution over unentailed visual factors. Given an input prompt ti, sampling random seeds induces a conditional image distribution PG(I∣ti), and we quantify the resulting unentailed attributes a∈/Entailed(ti) (Eq. 1) empirically via f(a∣ti) (Eq. 2) and PG(i) (Eq. 7). Prevalent implicit visual priors correspond to high-probability modes over these unentailed attributes, while Lift and JSD/Jk capture intra-prompt attribute dependencies and cross-model distributional divergence, respectively. By design, ProbeGen characterizes what a model internally defaults to without benchmarking against a real-world or uniform reference distribution. Consequently, it does not attempt to separate benign defaults and co-occurrences from harmful stereotypes, motivating our broader framing around "implicit visual priors."
We will incorporate these clarifications into the final version of the paper.