相关论文: EXPERT: An Explainable Image Captioning Evaluation…

To establish the trustworthiness of systems that automatically generate text captions for audio, images and video, existing reference-free metrics rely on large pretrained models which are impractical to accommodate in resource-constrained…

We propose a method that can generate an unambiguous description (known as a referring expression) of a specific object or region in an image, and which can also comprehend or interpret such an expression to infer which object is being…

An image caption should fluently present the essential information in a given image, including informative, fine-grained entity mentions and the manner in which these entities interact. However, current captioning models are usually trained…

Achieving human-level performance on some of Machine Reading Comprehension (MRC) datasets is no longer challenging with the help of powerful Pre-trained Language Models (PLMs). However, it is necessary to provide both answer prediction and…

In question answering requiring common sense, language models (e.g., GPT-3) have been used to generate text expressing background knowledge that helps improve performance. Yet the cost of working with such models is very high; in this work,…

With the rapid advancement of generative AI, synthetic content across images, videos, and audio has become increasingly realistic, amplifying the risk of misinformation. Existing detection approaches predominantly focus on binary…

Image classification is an essential part of computer vision which assigns a given input image to a specific category based on the similarity evaluation within given criteria. While promising classifiers can be obtained through deep…

We present iBERT (interpretable-BERT), an encoder to produce inherently interpretable and controllable embeddings - designed to modularize and expose the discriminative cues present in language, such as semantic or stylistic structure. Each…

Pre-trained language models (PLMs) like BERT are being used for almost all language-related tasks, but interpreting their behavior still remains a significant challenge and many important questions remain largely unanswered. In this work,…

The growing need for trustworthy machine learning has led to the blossom of interpretability research. Numerous explanation methods have been developed to serve this purpose. However, these methods are deficiently and inappropriately…

Neural networks lack the ability to reason about qualitative physics and so cannot generalize to scenarios and tasks unseen during training. We propose ESPRIT, a framework for commonsense reasoning about qualitative physics in natural…

Recent work has shown that inference-time reasoning and reflection can improve text-to-image generation without retraining. However, existing approaches often rely on implicit, holistic critiques or unconstrained prompt rewrites, making…

Given the accelerating progress of vision and language modeling, accurate evaluation of machine-generated image captions remains critical. In order to evaluate captions more closely to human preferences, metrics need to discriminate between…

Recently, reference-free metrics such as CLIPScore (Hessel et al., 2021), UMIC (Lee et al., 2021), and PAC-S (Sarto et al., 2023) have been proposed for automatic reference-free evaluation of image captions. Our focus lies in evaluating the…

Concept-based explanations work by mapping complex model computations to human-understandable concepts. Evaluating such explanations is very difficult, as it includes not only the quality of the induced space of possible concepts but also…

Image captioning evaluation metrics can be divided into two categories, reference-based metrics and reference-free metrics. However, reference-based approaches may struggle to evaluate descriptive captions with abundant visual details…

Explainable artificial intelligence is proposed to provide explanations for reasoning performed by an Artificial Intelligence. There is no consensus on how to evaluate the quality of these explanations, since even the definition of…

Recent advances in multi-modal generative models have enabled significant progress in instruction-based image editing. However, while these models produce visually plausible outputs, their capacity for knowledge-based reasoning editing…

Correct answers do not necessarily reflect cultural understanding. We introduce CRaFT, an explanation-based multilingual evaluation framework designed to assess how large language models (LLMs) reason across cultural contexts. Rather than…

While pre-trained language models achieve impressive performance on various NLP benchmarks, they still struggle with tasks that require numerical reasoning. Recent advances in improving numerical reasoning are mostly achieved using very…