Related papers: Trust but Verify: Programmatic VLM Evaluation in the Wild

Trust but Verify: Programmatic VLM Evaluation in the Wild

URL: http://arxiv.org/abs/2410.13121v1
Date: Thu, 17 Oct 2024 01:19:18 GMT
Title: Trust but Verify: Programmatic VLM Evaluation in the Wild
Authors: Viraj Prabhu, Senthil Purushwalkam, An Yan, Caiming Xiong, Ran Xu,
Abstract summary: Programmatic VLM Evaluation (PROVE) is a new benchmarking paradigm for evaluating VLM responses to open-ended queries. We benchmark the helpfulness-truthfulness trade-offs of a range ofVLMs on PROVE, finding that very few are in-fact able to achieve a good balance between the two.
Score: 62.14071929143684
License:
Abstract: Vision-Language Models (VLMs) often generate plausible but incorrect responses to visual queries. However, reliably quantifying the effect of such hallucinations in free-form responses to open-ended queries is challenging as it requires visually verifying each claim within the response. We propose Programmatic VLM Evaluation (PROVE), a new benchmarking paradigm for evaluating VLM responses to open-ended queries. To construct PROVE, we provide a large language model (LLM) with a high-fidelity scene-graph representation constructed from a hyper-detailed image caption, and prompt it to generate diverse question-answer (QA) pairs, as well as programs that can be executed over the scene graph object to verify each QA pair. We thus construct a benchmark of 10.5k challenging but visually grounded QA pairs. Next, to evaluate free-form model responses to queries in PROVE, we propose a programmatic evaluation strategy that measures both the helpfulness and truthfulness of a response within a unified scene graph-based framework. We benchmark the helpfulness-truthfulness trade-offs of a range of VLMs on PROVE, finding that very few are in-fact able to achieve a good balance between the two. Project page: \url{https://prove-explorer.netlify.app/}.

Related papers

AutoBench-V: Can Large Vision-Language Models Benchmark Themselves? [55.14033256706175]
Large Vision-Language Models (LVLMs) have become essential for advancing the integration of visual and linguistic information. We introduce AutoBench-V, an automated framework for serving evaluation on demand. Through an extensive evaluation of seven popular LVLMs across five demanded user inputs, the framework shows effectiveness and reliability.
arXiv Detail & Related papers (2024-10-28T17:55:08Z)
Declarative Knowledge Distillation from Large Language Models for Visual Question Answering Datasets [9.67464173044675]
Visual Question Answering (VQA) is the task of answering a question about an image. We present an approach for declarative knowledge distillation from Large Language Models (LLMs) Our results confirm that distilling knowledge from LLMs is in fact a promising direction besides data-driven rule learning approaches.
arXiv Detail & Related papers (2024-10-12T08:17:03Z)
S-EQA: Tackling Situational Queries in Embodied Question Answering [48.43453390717167]
We present and tackle the problem of Embodied Question Answering with Situational Queries (S-EQA) in a household environment. We first introduce a novel Prompt-Generate-Evaluate scheme that wraps around an LLM's output to create a dataset of unique situational queries and corresponding consensus object information. We report an improved accuracy of 15.31% while using queries framed from the generated object consensus for Visual Question Answering (VQA) over directly answering situational ones.
arXiv Detail & Related papers (2024-05-08T00:45:20Z)
VISREAS: Complex Visual Reasoning with Unanswerable Questions [29.398956873585796]
We introduce a new compositional visual question-answering dataset, VISREAS. It consists of answerable and unanswerable visual queries formulated by traversing and perturbing commonalities and differences among objects, attributes, and relations. The unique feature of this task, validating question answerability with respect to an image before answering, and the poor performance of state-of-the-art models inspired the design of a new modular baseline, LOGIC2VISION.
arXiv Detail & Related papers (2024-02-23T00:12:10Z)
Rephrase, Augment, Reason: Visual Grounding of Questions for Vision-Language Models [59.05769810380928]
Rephrase, Augment and Reason (RepARe) is a gradient-free framework that extracts salient details about the image using the underlying vision-language model. We show that RepARe can result in a 3.85% (absolute) increase in zero-shot accuracy on VQAv2, 6.41%, and 7.94% points increase on A-OKVQA, and VizWiz respectively.
arXiv Detail & Related papers (2023-10-09T16:57:57Z)
Investigating Prompting Techniques for Zero- and Few-Shot Visual Question Answering [7.640416680391081]
In this paper, we explore effective prompting techniques to enhance zero- and few-shot Visual Question Answering (VQA) performance. We identify that specific templates significantly influence VQA outcomes, underscoring the need for strategic template selection. To mitigate the challenges associated with evaluating free-form open-ended VQA responses, we introduce a straightforward LLM-guided pre-processing technique.
arXiv Detail & Related papers (2023-06-16T17:47:57Z)
How to Design Sample and Computationally Efficient VQA Models [53.65668097847456]
We find that representing the text as probabilistic programs and images as object-level scene graphs best satisfy these desiderata. We extend existing models to leverage these soft programs and scene graphs to train on question answer pairs in an end-to-end manner.
arXiv Detail & Related papers (2021-03-22T01:48:16Z)
A Revised Generative Evaluation of Visual Dialogue [80.17353102854405]
We propose a revised evaluation scheme for the VisDial dataset. We measure consensus between answers generated by the model and a set of relevant answers. We release these sets and code for the revised evaluation scheme as DenseVisDial.
arXiv Detail & Related papers (2020-04-20T13:26:45Z)

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