Related papers: HistLens: Mapping Idea Change across Concepts and …

Estimating the semantic similarity between text data is one of the challenging and open research problems in the field of Natural Language Processing (NLP). The versatility of natural language makes it difficult to define rule-based methods…

Metaphors are everywhere. They appear extensively across all domains of natural language, from the most sophisticated poetry to seemingly dry academic prose. A significant body of research in the cognitive science of language argues for the…

The meanings and relationships of words shift over time. This phenomenon is referred to as semantic shift. Research focused on understanding how semantic shifts occur over multiple time periods is essential for gaining a detailed…

With the growing popularity of general-purpose Large Language Models (LLMs), comes a need for more global explanations of model behaviors. Concept-based explanations arise as a promising avenue for explaining high-level patterns learned by…

This demonstration paper presents $\mathbf{LayLens}$, a tool aimed to make deepfake understanding easier for users of all educational backgrounds. While prior works often rely on outputs containing technical jargon, LayLens bridges the gap…

How universal is human conceptual structure? The way concepts are organized in the human brain may reflect distinct features of cultural, historical, and environmental background in addition to properties universal to human cognition.…

A key challenge in video question answering is how to realize the cross-modal semantic alignment between textual concepts and corresponding visual objects. Existing methods mostly seek to align the word representations with the video…

Multi-modal Large Language Models (MLLMs) have demonstrated remarkable capabilities in understanding and generating content across various modalities, such as images and text. However, their interpretability remains a challenge, hindering…

While Large Language Models (LLMs) achieve strong performance across diverse tasks, their inference dynamics remain poorly understood because of the limited resolution of existing analysis tools. In this work, we identify an intrinsic…

Concept-based models aim to explain model decisions with human-understandable concepts. However, most existing approaches treat concepts as numerical attributes, without providing complementary visual explanations that could localize the…

Visually-grounded spoken language datasets can enable models to learn cross-modal correspondences with very weak supervision. However, modern audio-visual datasets contain biases that undermine the real-world performance of models trained…

Recent advances in large language models (LLMs) have led to remarkable progress across domains, yet their capabilities in the humanities, particularly history, remain underexplored. Historical reasoning poses unique challenges for AI,…

There has been a considerable advance in computing, to mimic the way in which the brain tries to comprehend and structure the information to retrieve meaningful knowledge. It is identified that neuronal entities hold whole of the knowledge…

Traditional deep learning interpretability methods which are suitable for model users cannot explain network behaviors at the global level and are inflexible at providing fine-grained explanations. As a solution, concept-based explanations…

Multimodal health sensing offers rich behavioral signals for assessing mental health, yet translating these numerical time-series measurements into natural language remains challenging. Current LLMs cannot natively ingest long-duration…

Multimodal Large Language Models (MLLMs) have advanced in integrating diverse modalities but frequently suffer from hallucination. A promising solution to mitigate this issue is to generate text with citations, providing a transparent chain…

Skeleton-based human action recognition has achieved remarkable progress in recent years. However, most existing GCN-based methods rely on short-range motion topologies, which not only struggle to capture long-range joint dependencies and…

Models based on human-understandable concepts have received extensive attention to improve model interpretability for trustworthy artificial intelligence in the field of medical image analysis. These methods can provide convincing…

Entity-level sentiment classification involves identifying the sentiment polarity linked to specific entities within text. This task poses several challenges: effectively modeling the subtle and complex interactions between entities and…

Machine learning models that first learn a representation of a domain in terms of human-understandable concepts, then use it to make predictions, have been proposed to facilitate interpretation and interaction with models trained on…