相关论文: Zero-Shot Classification by Logical Reasoning on N…

We introduce CLEAR (Contrasting Textual Feedback with Experts and Amateurs for Reasoning), a novel approach to language model reasoning that leverages the strengths of a larger (expert) model and smaller (amateur) model. The expert and…

The overarching goal of Explainable AI is to develop systems that not only exhibit intelligent behaviours, but also are able to explain their rationale and reveal insights. In explainable machine learning, methods that produce a high level…

Recent years have witnessed an increasing interest in training machines with reasoning ability, which deeply relies on accurately and clearly presented clue forms. The clues are usually modeled as entity-aware knowledge in existing studies.…

Humans can obtain the knowledge of novel visual concepts from language descriptions, and we thus use the few-shot image classification task to investigate whether a machine learning model can have this capability. Our proposed model, LIDE…

Fairness-aware machine learning has attracted a surge of attention in many domains, such as online advertising, personalized recommendation, and social media analysis in web applications. Fairness-aware machine learning aims to eliminate…

Recent works in Explainable AI mostly address the transparency issue of black-box models or create explanations for any kind of models (i.e., they are model-agnostic), while leaving explanations of interpretable models largely…

Zero-shot inference, where pre-trained models perform tasks without specific training data, is an exciting emergent ability of large models like CLIP. Although there has been considerable exploration into enhancing zero-shot abilities in…

Zero-shot textual explanations aim to make image classifiers more transparent by probing their internal representations, without relying on task-specific supervision or LVLMs. However, existing methods often miss the features that truly…

Large-scale vision-language models such as CLIP have achieved remarkable success in zero-shot image recognition, yet their predictions remain largely opaque to human understanding. In contrast, Concept Bottleneck Models provide…

Online medical service provides patients convenient access to doctors, but effectively ranking doctors based on specific medical needs remains challenging. Current ranking approaches typically lack the interpretability crucial for patient…

Benefiting from strong generalization ability, pre-trained vision language models (VLMs), e.g., CLIP, have been widely utilized in zero-shot scene understanding. Unlike simple recognition tasks, grounded situation recognition (GSR) requires…

Open-vocabulary models are a promising new paradigm for image classification. Unlike traditional classification models, open-vocabulary models classify among any arbitrary set of categories specified with natural language during inference.…

Black box systems for automated decision making, often based on machine learning over (big) data, map a user's features into a class or a score without exposing the reasons why. This is problematic not only for lack of transparency, but…

Zero-shot object-goal navigation (ZSON) is a challenging problem in robotics that requires a comprehensive understanding of both language and visual observations. Contextual cues from rooms and objects are critical, but their relative…

The pursuit of decision safety in clinical applications highlights the potential of concept-based methods in medical imaging. While these models offer active interpretability, they often suffer from concept leakages, where unintended…

A grammar formalism based upon CHR is proposed analogously to the way Definite Clause Grammars are defined and implemented on top of Prolog. These grammars execute as robust bottom-up parsers with an inherent treatment of ambiguity and a…

Companies regularly spend millions of dollars producing electronically-stored documents in legal matters. Recently, parties on both sides of the 'legal aisle' are accepting the use of machine learning techniques like text classification to…

Convincing someone of the truth value of a premise requires understanding and articulating the core logical structure of the argument which proves or disproves the premise. Understanding the logical structure of an argument refers to…

We consider a zero-shot semantic parsing task: parsing instructions into compositional logical forms, in domains that were not seen during training. We present a new dataset with 1,390 examples from 7 application domains (e.g. a calendar or…

Household environments are visually diverse. Embodied agents performing Vision-and-Language Navigation (VLN) in the wild must be able to handle this diversity, while also following arbitrary language instructions. Recently, Vision-Language…