Are vision language models robust to uncertain inputs?

• URL: http://arxiv.org/abs/2505.11804v1
• Date: Sat, 17 May 2025 03:16:49 GMT
• Title: Are vision language models robust to uncertain inputs?
• Authors: Xi Wang, Eric Nalisnick,
• Abstract summary: We show that newer and larger vision language models exhibit improved robustness compared to earlier models, but still suffer from a tendency to strictly follow instructions.<n>For natural images such as ImageNet, this limitation can be overcome without pipeline modifications.<n>We propose a novel mechanism based on caption diversity to reveal a model's internal uncertainty.
• Score: 5.249651874118556
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Robustness against uncertain and ambiguous inputs is a critical challenge for deep learning models. While recent advancements in large scale vision language models (VLMs, e.g. GPT4o) might suggest that increasing model and training dataset size would mitigate this issue, our empirical evaluation shows a more complicated picture. Testing models using two classic uncertainty quantification tasks, anomaly detection and classification under inherently ambiguous conditions, we find that newer and larger VLMs indeed exhibit improved robustness compared to earlier models, but still suffer from a tendency to strictly follow instructions, often causing them to hallucinate confident responses even when faced with unclear or anomalous inputs. Remarkably, for natural images such as ImageNet, this limitation can be overcome without pipeline modifications: simply prompting models to abstain from uncertain predictions enables significant reliability gains, achieving near-perfect robustness in several settings. However, for domain-specific tasks such as galaxy morphology classification, a lack of specialized knowledge prevents reliable uncertainty estimation. Finally, we propose a novel mechanism based on caption diversity to reveal a model's internal uncertainty, enabling practitioners to predict when models will successfully abstain without relying on labeled data.

Related papers

• Pretrained LLMs Learn Multiple Types of Uncertainty [23.807232455808613]
  Large Language Models are known to capture real-world knowledge, allowing them to excel in many downstream tasks.<n>In this work, we study how well LLMs capture uncertainty, without explicitly being trained for that.<n>We show that, if considering uncertainty as a linear concept in the model's latent space, it might indeed be captured, even after only pretraining.
  arXiv  Detail & Related papers  (2025-05-27T14:06:15Z)
• LoGU: Long-form Generation with Uncertainty Expressions [49.76417603761989]
  We introduce the task of Long-form Generation with Uncertainty(LoGU) We identify two key challenges: Uncertainty Suppression and Uncertainty Misalignment. Our framework adopts a divide-and-conquer strategy, refining uncertainty based on atomic claims. Experiments on three long-form instruction following datasets show that our method significantly improves accuracy, reduces hallucinations, and maintains the comprehensiveness of responses.
  arXiv  Detail & Related papers  (2024-10-18T09:15:35Z)
• Unsupervised Model Diagnosis [49.36194740479798]
  This paper proposes Unsupervised Model Diagnosis (UMO) to produce semantic counterfactual explanations without any user guidance. Our approach identifies and visualizes changes in semantics, and then matches these changes to attributes from wide-ranging text sources.
  arXiv  Detail & Related papers  (2024-10-08T17:59:03Z)
• Adversarial Robustification via Text-to-Image Diffusion Models [56.37291240867549]
  Adrial robustness has been conventionally believed as a challenging property to encode for neural networks. We develop a scalable and model-agnostic solution to achieve adversarial robustness without using any data.
  arXiv  Detail & Related papers  (2024-07-26T10:49:14Z)
• An Ambiguity Measure for Recognizing the Unknowns in Deep Learning [0.0]
  We study the understanding of deep neural networks from the scope in which they are trained on. We propose a measure for quantifying the ambiguity of inputs for any given model.
  arXiv  Detail & Related papers  (2023-12-11T02:57:12Z)
• Decomposing Uncertainty for Large Language Models through Input Clarification Ensembling [69.83976050879318]
  In large language models (LLMs), identifying sources of uncertainty is an important step toward improving reliability, trustworthiness, and interpretability. In this paper, we introduce an uncertainty decomposition framework for LLMs, called input clarification ensembling. Our approach generates a set of clarifications for the input, feeds them into an LLM, and ensembles the corresponding predictions.
  arXiv  Detail & Related papers  (2023-11-15T05:58:35Z)
• Improving the Reliability of Large Language Models by Leveraging Uncertainty-Aware In-Context Learning [76.98542249776257]
  Large-scale language models often face the challenge of "hallucination" We introduce an uncertainty-aware in-context learning framework to empower the model to enhance or reject its output in response to uncertainty.
  arXiv  Detail & Related papers  (2023-10-07T12:06:53Z)
• Beyond Confidence: Reliable Models Should Also Consider Atypicality [43.012818086415514]
  We investigate the relationship between how atypical(rare) a sample or a class is and the reliability of a model's predictions. We show that predictions for atypical inputs or atypical classes are more overconfident and have lower accuracy. We propose that models should use not only confidence but also atypicality to improve uncertainty quantification and performance.
  arXiv  Detail & Related papers  (2023-05-29T17:37:09Z)
• ALUM: Adversarial Data Uncertainty Modeling from Latent Model Uncertainty Compensation [25.67258563807856]
  We propose a novel method called ALUM to handle the model uncertainty and data uncertainty in a unified scheme. Our proposed ALUM is model-agnostic which can be easily implemented into any existing deep model with little extra overhead.
  arXiv  Detail & Related papers  (2023-03-29T17:24:12Z)
• BayesCap: Bayesian Identity Cap for Calibrated Uncertainty in Frozen Neural Networks [50.15201777970128]
  We propose BayesCap that learns a Bayesian identity mapping for the frozen model, allowing uncertainty estimation. BayesCap is a memory-efficient method that can be trained on a small fraction of the original dataset. We show the efficacy of our method on a wide variety of tasks with a diverse set of architectures.
  arXiv  Detail & Related papers  (2022-07-14T12:50:09Z)
• Approaching Neural Network Uncertainty Realism [53.308409014122816]
  Quantifying or at least upper-bounding uncertainties is vital for safety-critical systems such as autonomous vehicles. We evaluate uncertainty realism -- a strict quality criterion -- with a Mahalanobis distance-based statistical test. We adopt it to the automotive domain and show that it significantly improves uncertainty realism compared to a plain encoder-decoder model.
  arXiv  Detail & Related papers  (2021-01-08T11:56:12Z)
• Model Uncertainty Quantification for Reliable Deep Vision Structural Health Monitoring [2.5126058470073263]
  This paper proposes Bayesian inference for deep vision structural health monitoring models. Uncertainty can be quantified using the Monte Carlo dropout sampling. Three independent case studies for cracks, local damage identification, and bridge component detection are investigated.
  arXiv  Detail & Related papers  (2020-04-10T17:54:10Z)

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.