Related papers: Hallucination Improves the Performance of Unsuperv…

Despite improvements in performances on different natural language generation tasks, deep neural models are prone to hallucinating facts that are incorrect or nonexistent. Different hypotheses are proposed and examined separately for…

Multimodal Large Language Models (MLLMs) excel in vision-language tasks such as image captioning but remain prone to object hallucinations, where they describe objects that do not appear in the image. To mitigate this, we propose LISA, a…

Despite the impressive advancements made in recent low-light image enhancement techniques, the scarcity of paired data has emerged as a significant obstacle to further advancements. This work proposes a mean-teacher-based semi-supervised…

Unsupervised learning has been a long-standing goal of machine learning and is especially important for medical image analysis, where the learning can compensate for the scarcity of labeled datasets. A promising subclass of unsupervised…

In this paper, we are interested in understanding self-supervised pretraining through studying the capability that self-supervised representation pretraining methods learn part-aware representations. The study is mainly motivated by that…

Contrastive learning between different views of the data achieves outstanding success in the field of self-supervised representation learning and the learned representations are useful in broad downstream tasks. Since all supervision…

Contrastive learning is among the most successful methods for visual representation learning, and its performance can be further improved by jointly performing clustering on the learned representations. However, existing methods for joint…

Large Vision-Language Models (LVLMs) have achieved impressive performance, yet research has pointed out a serious issue with object hallucinations within these models. However, there is no clear conclusion as to which part of the model…

Contrastive unsupervised learning has recently shown encouraging progress, e.g., in Momentum Contrast (MoCo) and SimCLR. In this note, we verify the effectiveness of two of SimCLR's design improvements by implementing them in the MoCo…

Contrastive learning -- a modern approach to extract useful representations from unlabeled data by training models to distinguish similar samples from dissimilar ones -- has driven significant progress in foundation models. In this work, we…

Object hallucination remains a primary obstacle to the reliable deployment of Multimodal Large Language Models (MLLMs). Current inference-time mitigation methods mainly assume hallucinations stem from visual neglect, steering models to…

Recent self-supervised contrastive methods have been able to produce impressive transferable visual representations by learning to be invariant to different data augmentations. However, these methods implicitly assume a particular set of…

While contrastive learning is proven to be an effective training strategy in computer vision, Natural Language Processing (NLP) is only recently adopting it as a self-supervised alternative to Masked Language Modeling (MLM) for improving…

Self-supervised learning (especially contrastive learning) has attracted great interest due to its huge potential in learning discriminative representations in an unsupervised manner. Despite the acknowledged successes, existing contrastive…

When asked to summarize articles or answer questions given a passage, large language models (LLMs) can hallucinate details and respond with unsubstantiated answers that are inaccurate with respect to the input context. This paper describes…

Representation learning has significantly been developed with the advance of contrastive learning methods. Most of those methods have benefited from various data augmentations that are carefully designated to maintain their identities so…

Recent contrastive methods show significant improvement in self-supervised learning in several domains. In particular, contrastive methods are most effective where data augmentation can be easily constructed e.g. in computer vision.…

While state-of-the-art contrastive Self-Supervised Learning (SSL) models produce results competitive with their supervised counterparts, they lack the ability to infer latent variables. In contrast, prescribed latent variable (LV) models…

Hallucination remains a key obstacle to the reliable deployment of large language models (LLMs) in real-world question answering tasks. A widely adopted strategy to detect hallucination, known as self-assessment, relies on the model's own…

Large language models (LLMs) demonstrate strong capabilities in natural language processing but remain prone to hallucinations, generating factually incorrect or fabricated content. This issue undermines their reliability, particularly in…