Related papers: Zero-Shot Event Causality Identification via Multi…

Recent advances in large language models (LLMs) have significantly impacted the domain of multi-hop question answering (MHQA), where systems are required to aggregate information and infer answers from disparate pieces of text. However, the…

Video causal reasoning aims to achieve a high-level understanding of videos from a causal perspective. However, it exhibits limitations in its scope, primarily executed in a question-answering paradigm and focusing on brief video segments…

The advancements in large language models (LLMs) have brought significant progress in NLP tasks. However, if a task cannot be fully described in prompts, the models could fail to carry out the task. In this paper, we propose a simple yet…

Despite the groundbreaking advancements made by large language models (LLMs), hallucination remains a critical bottleneck for their deployment in high-stakes domains. Existing classification-based methods mainly rely on static and passive…

As large language models (LLMs) witness increasing deployment in complex, high-stakes decision-making scenarios, it becomes imperative to ground their reasoning in causality rather than spurious correlations. However, strong performance on…

Hallucinations, generating responses inconsistent with the visual input, remain a critical limitation of large vision-language models (LVLMs), especially in open-ended tasks such as image captioning and visual reasoning. In this work, we…

Although large language models (LLMs) excel in complex reasoning tasks, they suffer from severe causal hallucination in event causality identification (ECI), particularly in smaller models ($\leq$1.5B parameters). A promising approach to…

Abstractive summarization systems leveraging pre-training language models have achieved superior results on benchmark datasets. However, such models have been shown to be more prone to hallucinate facts that are unfaithful to the input…

Multi-view unsupervised feature selection (MUFS) has recently received increasing attention for its promising ability in dimensionality reduction on multi-view unlabeled data. Existing MUFS methods typically select discriminative features…

Despite the remarkable advancements of Large Vision-Language Models (LVLMs), the mechanistic interpretability remains underexplored. Existing analyses are insufficiently comprehensive and lack examination covering visual and textual tokens,…

Fuzzy clustering methods identify naturally occurring clusters in a dataset, where the extent to which different clusters are overlapped can differ. Most methods have a parameter to fix the level of fuzziness. However, the appropriate level…

Action detection and understanding provide the foundation for the generation and interaction of multimedia content. However, existing methods mainly focus on constructing complex relational inference networks, overlooking the judgment of…

Combining pre-trained expert models offers substantial potential for scalable multimodal reasoning, but building a unified framework remains challenging due to the increasing diversity of input modalities and task complexity. For instance,…

The existing event classification (EC) work primarily focuseson the traditional supervised learning setting in which models are unableto extract event mentions of new/unseen event types. Few-shot learninghas not been investigated in this…

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…

Decentralized data sources are prevalent in real-world applications, posing a formidable challenge for causal inference. These sources cannot be consolidated into a single entity owing to privacy constraints. The presence of dissimilar data…

Recent advancements in Large Vision-Language Models (LVLMs) have significantly expanded their utility in tasks like image captioning and visual question answering. However, they still struggle with object hallucination, where models…

As few-shot object detectors are often trained with abundant base samples and fine-tuned on few-shot novel examples,the learned models are usually biased to base classes and sensitive to the variance of novel examples. To address this…

Cross-document Event Coreference Resolution (CD-ECR) is a fundamental task in natural language processing (NLP) that seeks to determine whether event mentions across multiple documents refer to the same real-world occurrence. However,…

Zero-shot learning (ZSL) extends the conventional image classification technique to a more challenging situation where the test image categories are not seen in the training samples. Most studies on ZSL utilize side information such as…