Consistency and Uncertainty: Identifying Unreliable Responses From Black-Box Vision-Language Models for Selective Visual Question Answering

• URL: http://arxiv.org/abs/2404.10193v1
• Date: Tue, 16 Apr 2024 00:28:26 GMT
• Title: Consistency and Uncertainty: Identifying Unreliable Responses From Black-Box Vision-Language Models for Selective Visual Question Answering
• Authors: Zaid Khan, Yun Fu,
• Abstract summary: We study the possibility of selective prediction for vision-language models in a realistic, black-box setting. We propose using the principle of textitneighborhood consistency to identify unreliable responses from a black-box vision-language model in question answering tasks.
• Score: 46.823415680462844
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The goal of selective prediction is to allow an a model to abstain when it may not be able to deliver a reliable prediction, which is important in safety-critical contexts. Existing approaches to selective prediction typically require access to the internals of a model, require retraining a model or study only unimodal models. However, the most powerful models (e.g. GPT-4) are typically only available as black boxes with inaccessible internals, are not retrainable by end-users, and are frequently used for multimodal tasks. We study the possibility of selective prediction for vision-language models in a realistic, black-box setting. We propose using the principle of \textit{neighborhood consistency} to identify unreliable responses from a black-box vision-language model in question answering tasks. We hypothesize that given only a visual question and model response, the consistency of the model's responses over the neighborhood of a visual question will indicate reliability. It is impossible to directly sample neighbors in feature space in a black-box setting. Instead, we show that it is possible to use a smaller proxy model to approximately sample from the neighborhood. We find that neighborhood consistency can be used to identify model responses to visual questions that are likely unreliable, even in adversarial settings or settings that are out-of-distribution to the proxy model.

Related papers

• Bounding-Box Inference for Error-Aware Model-Based Reinforcement Learning [4.185571779339683]
  In model-based reinforcement learning, simulated experiences are often treated as equivalent to experience from the real environment. We show that best results require distribution insensitive inference to estimate the uncertainty over model-based updates. We find that bounding-box inference can reliably support effective selective planning.
  arXiv  Detail & Related papers  (2024-06-23T04:23:15Z)
• Zero-shot Model Diagnosis [80.36063332820568]
  A common approach to evaluate deep learning models is to build a labeled test set with attributes of interest and assess how well it performs. This paper argues the case that Zero-shot Model Diagnosis (ZOOM) is possible without the need for a test set nor labeling.
  arXiv  Detail & Related papers  (2023-03-27T17:59:33Z)
• Realistic Conversational Question Answering with Answer Selection based on Calibrated Confidence and Uncertainty Measurement [54.55643652781891]
  Conversational Question Answering (ConvQA) models aim at answering a question with its relevant paragraph and previous question-answer pairs that occurred during conversation multiple times. We propose to filter out inaccurate answers in the conversation history based on their estimated confidences and uncertainties from the ConvQA model. We validate our models, Answer Selection-based realistic Conversation Question Answering, on two standard ConvQA datasets.
  arXiv  Detail & Related papers  (2023-02-10T09:42:07Z)
• Debiasing Vision-Language Models via Biased Prompts [79.04467131711775]
  We propose a general approach for debiasing vision-language foundation models by projecting out biased directions in the text embedding. We show that debiasing only the text embedding with a calibrated projection matrix suffices to yield robust classifiers and fair generative models.
  arXiv  Detail & Related papers  (2023-01-31T20:09:33Z)
• Uncertainty Quantification for Local Model Explanations Without Model Access [0.44241702149260353]
  We present a model-agnostic algorithm for generating post-hoc explanations for a machine learning model. Our algorithm uses a bootstrapping approach to quantify the uncertainty that inevitably arises when generating explanations from a finite sample of model queries.
  arXiv  Detail & Related papers  (2023-01-13T21:18:00Z)
• PRISM: Probabilistic Real-Time Inference in Spatial World Models [52.878769723544615]
  PRISM is a method for real-time filtering in a probabilistic generative model of agent motion and visual perception. The proposed solution runs at 10Hz real-time and is similarly accurate to state-of-the-art SLAM in small to medium-sized indoor environments.
  arXiv  Detail & Related papers  (2022-12-06T13:59:06Z)
• Post-Selection Confidence Bounds for Prediction Performance [2.28438857884398]
  In machine learning, the selection of a promising model from a potentially large number of competing models and the assessment of its generalization performance are critical tasks. We propose an algorithm how to compute valid lower confidence bounds for multiple models that have been selected based on their prediction performances in the evaluation set.
  arXiv  Detail & Related papers  (2022-10-24T13:28:43Z)
• Probabilistic Modeling for Human Mesh Recovery [73.11532990173441]
  This paper focuses on the problem of 3D human reconstruction from 2D evidence. We recast the problem as learning a mapping from the input to a distribution of plausible 3D poses.
  arXiv  Detail & Related papers  (2021-08-26T17:55:11Z)
• Learning Global Transparent Models Consistent with Local Contrastive Explanations [34.86847988157447]
  We create custom features from sparse local contrastive explanations of the black-box model and then train a globally transparent model on just these. Based on a key insight we propose a novel method where we create custom features from sparse local contrastive explanations of the black-box model and then train a globally transparent model on just these.
  arXiv  Detail & Related papers  (2020-02-19T15:45:42Z)
• Interpretable Companions for Black-Box Models [13.39487972552112]
  We present an interpretable companion model for any pre-trained black-box classifiers. For any input, a user can decide to either receive a prediction from the black-box model, with high accuracy but no explanations, or employ a companion rule to obtain an interpretable prediction with slightly lower accuracy. The companion model is trained from data and the predictions of the black-box model, with the objective combining area under the transparency--accuracy curve and model complexity.
  arXiv  Detail & Related papers  (2020-02-10T01:39:16Z)

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.