Probing Perceptual Priors of MLLMs via Gibbs Sampling with Interpretable Generative Controls

• URL: http://arxiv.org/abs/2608.27727v1
• Date: Thu, 27 Aug 2026 21:38:41 GMT
• Title: Probing Perceptual Priors of MLLMs via Gibbs Sampling with Interpretable Generative Controls
• Abstract summary: A model's behavior on a task is jointly determined by the input it receives and the prior it brings in, i.e. the distribution over stimuli it implicitly expects.<n>We propose a method to sample from models' perceptual prior distributions directly, by steering a generative model to produce stimuli along controllable axes and running Gibbs sampling over that space with the model under study as the judge.
• Score: 30.071130311851277
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: A model's behavior on a task is jointly determined by the input it receives and the prior it brings in, i.e. the distribution over stimuli it implicitly expects. Interpretability research has traditionally studied models by holding inputs fixed and examining model responses either mechanistically, probing how internal structure represents inputs, or behaviorally, measuring how variation in inputs leads to variation in outputs. Neither reconstructs the prior distribution itself, since internal structure shows what a model can represent, not what it expects, and any fixed stimulus set leaves most of the possible input space unseen. In particular, such an input space in real-world settings, such as images seen by VLMs, is extremely high-dimensional and diverse. These priors thus remain a poorly understood component of models that nonetheless influence real-world behavior. We propose a method to sample from models' perceptual prior distributions directly, by steering a generative model to produce stimuli along controllable axes and running Gibbs sampling over that space with the model under study as the judge. We apply this to a variety of categories and target variables (such as trustworthiness in faces and cheapness in art images) and recover both canonical biases and surprising novel priors invisible to direct prompting, warranting further investigation of their downstream effects.

Related papers

• APEX: Probing Neural Networks via Activation Perturbation [10.517751599566548]
  We introduce Activation Perturbation for EXploration (APEX) as an inference-time probing paradigm for neural networks.<n>APEX perturbs hidden activations while keeping both inputs and model parameters fixed.<n>Our results show that APEX offers an effective perspective for exploring, and understanding neural networks beyond what is accessible from input space alone.
  arXiv  Detail & Related papers  (2026-02-03T14:36:36Z)
• Did Models Sufficient Learn? Attribution-Guided Training via Subset-Selected Counterfactual Augmentation [61.248535801314375]
  Subset-Selected Counterfactual Augmentation (SS-CA)<n>We develop Counterfactual LIMA to identify minimal spatial region sets whose removal can selectively alter model predictions.<n>Experiments show that SS-CA improves generalization on in-distribution (ID) test data and achieves superior performance on out-of-distribution (OOD) benchmarks.
  arXiv  Detail & Related papers  (2025-11-15T08:39:22Z)
• Can Interpretation Predict Behavior on Unseen Data? [11.280404893713213]
  Interpretability research often aims to predict how a model will respond to targeted interventions on specific mechanisms.<n>This paper explores the promises and challenges of interpretability as a tool for predicting out-of-distribution model behavior.
  arXiv  Detail & Related papers  (2025-07-08T23:07:33Z)
• Internal Causal Mechanisms Robustly Predict Language Model Out-of-Distribution Behaviors [61.92704516732144]
  We show that the most robust features for correctness prediction are those that play a distinctive causal role in the model's behavior.<n>We propose two methods that leverage causal mechanisms to predict the correctness of model outputs.
  arXiv  Detail & Related papers  (2025-05-17T00:31:39Z)
• Predicting the Performance of Black-box LLMs through Self-Queries [60.87193950962585]
  Large language models (LLMs) are increasingly relied on in AI systems, predicting when they make mistakes is crucial.<n>In this paper, we extract features of LLMs in a black-box manner by using follow-up prompts and taking the probabilities of different responses as representations.<n>We demonstrate that training a linear model on these low-dimensional representations produces reliable predictors of model performance at the instance level.
  arXiv  Detail & Related papers  (2025-01-02T22:26:54Z)
• Causal Analysis for Robust Interpretability of Neural Networks [0.2519906683279152]
  We develop a robust interventional-based method to capture cause-effect mechanisms in pre-trained neural networks. We apply our method to vision models trained on classification tasks.
  arXiv  Detail & Related papers  (2023-05-15T18:37:24Z)
• Certifying Model Accuracy under Distribution Shifts [151.67113334248464]
  We present provable robustness guarantees on the accuracy of a model under bounded Wasserstein shifts of the data distribution. We show that a simple procedure that randomizes the input of the model within a transformation space is provably robust to distributional shifts under the transformation.
  arXiv  Detail & Related papers  (2022-01-28T22:03:50Z)
• Explain, Edit, and Understand: Rethinking User Study Design for Evaluating Model Explanations [97.91630330328815]
  We conduct a crowdsourcing study, where participants interact with deception detection models that have been trained to distinguish between genuine and fake hotel reviews. We observe that for a linear bag-of-words model, participants with access to the feature coefficients during training are able to cause a larger reduction in model confidence in the testing phase when compared to the no-explanation control.
  arXiv  Detail & Related papers  (2021-12-17T18:29:56Z)
• Recoding latent sentence representations -- Dynamic gradient-based activation modification in RNNs [0.0]
  In RNNs, encoding information in a suboptimal way can impact the quality of representations based on later elements in the sequence. I propose an augmentation to standard RNNs in form of a gradient-based correction mechanism. I conduct different experiments in the context of language modeling, where the impact of using such a mechanism is examined in detail.
  arXiv  Detail & Related papers  (2021-01-03T17:54:17Z)
• Estimating Generalization under Distribution Shifts via Domain-Invariant Representations [75.74928159249225]
  We use a set of domain-invariant predictors as a proxy for the unknown, true target labels. The error of the resulting risk estimate depends on the target risk of the proxy model.
  arXiv  Detail & Related papers  (2020-07-06T17:21:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.