Related papers: Few-Shot Optimized Framework for Hallucination Det…

Few-shot Learning aims to learn and distinguish new categories with a very limited number of available images, presenting a significant challenge in the realm of deep learning. Recent researchers have sought to leverage the additional…

Few-shot classification requires adapting knowledge learned from a large annotated base dataset to recognize novel unseen classes, each represented by few labeled examples. In such a scenario, pretraining a network with high capacity on the…

Learning new concepts from a few of samples is a standard challenge in computer vision. The main directions to improve the learning ability of few-shot training models include (i) a robust similarity learning and (ii) generating or…

We describe the University of Amsterdam Intelligent Data Engineering Lab team's entry for the SemEval-2024 Task 6 competition. The SHROOM-INDElab system builds on previous work on using prompt programming and in-context learning with large…

Learning to recognize novel concepts from just a few image samples is very challenging as the learned model is easily overfitted on the few data and results in poor generalizability. One promising but underexplored solution is to compensate…

Hallucinations in Large Language Models (LLMs) pose a major barrier to their reliable use in critical decision-making. Although existing hallucination detection methods have improved accuracy, they still struggle with disentangling semantic…

Few-shot natural language processing (NLP) refers to NLP tasks that are accompanied with merely a handful of labeled examples. This is a real-world challenge that an AI system must learn to handle. Usually we rely on collecting more…

This work introduces a novel methodology for the automatic detection of hallucinations generated during large language model (LLM) inference. The proposed approach is based on a systematic taxonomy and controlled reproduction of diverse…

Text classification tends to be difficult when data are deficient or when it is required to adapt to unseen classes. In such challenging scenarios, recent studies have often used meta-learning to simulate the few-shot task, thus negating…

Learning to detect novel objects from few annotated examples is of great practical importance. A particularly challenging yet common regime occurs when there are extremely limited examples (less than three). One critical factor in improving…

Objective: Few-shot learning (FSL) methods require small numbers of labeled instances for training. As many medical topics have limited annotated textual data in practical settings, FSL-based natural language processing (NLP) methods hold…

Few-shot learning is a promising way for reducing the label cost in new categories adaptation with the guidance of a small, well labeled support set. But for few-shot semantic segmentation, the pixel-level annotations of support images are…

Large language models (LLMs) have achieved remarkable success in various natural language processing tasks, yet they remain prone to generating factually incorrect outputs known as hallucinations. While recent approaches have shown promise…

In recent studies, the extensive utilization of large language models has underscored the importance of robust evaluation methodologies for assessing text generation quality and relevance to specific tasks. This has revealed a prevalent…

Large-scale pre-trained Vision-Language Models (VLMs) have exhibited impressive zero-shot performance and transferability, allowing them to adapt to downstream tasks in a data-efficient manner. However, when only a few labeled samples are…

Low-shot visual learning---the ability to recognize novel object categories from very few examples---is a hallmark of human visual intelligence. Existing machine learning approaches fail to generalize in the same way. To make progress on…

Large Multimodal Models (LMMs) have achieved impressive progress in visual perception and reasoning. However, when confronted with visually ambiguous or non-semantic scene text, they often struggle to accurately spot and understand the…

This paper presents our findings of the Multilingual Shared Task on Hallucinations and Related Observable Overgeneration Mistakes, MU-SHROOM, which focuses on identifying hallucinations and related overgeneration errors in large language…

Most computer aided pathology detection systems rely on large volumes of quality annotated data to aid diagnostics and follow up procedures. However, quality assuring large volumes of annotated medical image data can be subjective and…

Vision-language models (VLMs) frequently generate hallucinated content plausible but incorrect claims about image content. We propose a training-free self-correction framework enabling VLMs to iteratively refine responses through…