Search papers, labs, and topics across Lattice.
To eliminate the prohibitive computational cost of sampling-heavy bias evaluations across classifier-free guidance scales, this work casts the diffusion process into a structural causal model abstracted over high-level denoising states. The authors prove the identifiability of fairness-relevant interventional queries under this causal abstraction and instantiate the surrogate with an amortized probabilistic transformer. Evaluated on Stable Diffusion 1.5 and StayFair, the method accurately predicts demographic feature distributions across guidance sweeps while drastically reducing inference overhead.
Auditing demographic bias across guidance scales no longer requires brute-force image generation: causal abstraction enables a lightweight transformer to predict fairness shifts across the entire CFG spectrum.
Fairness auditing of text-to-image diffusion models often requires generating large numbers of images across sampling configurations, making comprehensive evaluation computationally expensive. We propose a causal-abstraction-based audit instrument for efficiently evaluating fairness under interventions on the classifier-free guidance scale. Given a fixed prompt and a target feature function, we represent the diffusion process as a low-level structural causal model and construct a corresponding high-level model over abstract denoising states. We characterize the projected causal structure, establish identifiability of the fairness-relevant interventional query, and provide sufficient conditions under which the high-level model preserves this query. A probabilistic transformer implements the high-level model as an amortized predictor of target-feature distributions across guidance scales. Experiments evaluate distributional fidelity, fairness-query accuracy, and computational efficiency. We present two auditing demonstrations: one using standard Stable Diffusion 1.5 and another using StayFair, a fairness-enhanced Stable Diffusion model, to examine their behavior across guidance scales.
