Related papers: TOPol: Capturing and Explaining Multidimensional S…
Most intrinsic association probes operate at the word, sentence, or corpus level, obscuring author-level variation. We present POLAR (Per-user On-axis Lexical Association Re-port), a per-user lexical association test that runs in the…
In the retrieval-based multi-turn dialogue modeling, it remains a challenge to select the most appropriate response according to extracting salient features in context utterances. As a conversation goes on, topic shift at discourse-level…
Sentiment analysis possesses the potential of diverse applicability on digital platforms. Sentiment analysis extracts the polarity to understand the intensity and subjectivity in the text. This work uses a lexicon-based method to perform…
Large Language Models like GPT-4 adjust their responses not only based on the question asked, but also on how it is emotionally phrased. We systematically vary the emotional tone of 156 prompts - spanning controversial and everyday topics -…
Recent years have witnessed a surge of research on leveraging large language models (LLMs) for sequential recommendation. LLMs have demonstrated remarkable potential in inferring users' nuanced preferences through fine-grained semantic…
Higher-order topological phases (HOTPs) host exotic topological states that go beyond the traditional bulk-boundary correspondence. Up to now, there is still a lack of experimentally measurable momentum-space topological characterization…
This paper investigates how Transformer language models (LMs) fine-tuned for acceptability classification capture linguistic features. Our approach uses the best practices of topological data analysis (TDA) in NLP: we construct directed…
Mobile robots require comprehensive scene understanding to operate effectively in diverse environments, enriched with contextual information such as layouts, objects, and their relationships. Although advances like neural radiation fields…
Ontologies are formal representations of concepts and complex relationships among them. They have been widely used to capture comprehensive domain knowledge in areas such as biology and medicine, where large and complex ontologies can…
Every culture and language is unique. Our work expressly focuses on the uniqueness of culture and language in relation to human affect, specifically sentiment and emotion semantics, and how they manifest in social multimedia. We develop…
Large Vision-Language Models (LVLMs) map visual inputs into dense token sequences, imposing a quadratic computational bottleneck for inference. Elastic visual-token compression addresses this by training a single model that can run at…
Many complex scenarios require the coordination of agents possessing unique points of view and distinct semantic commitments. In response, standpoint logic (SL) was introduced in the context of knowledge integration, allowing one to reason…
Can warping tokens, rather than pixels, help multimodal large language models (MLLMs) understand how a scene appears from a nearby viewpoint? While MLLMs perform well on visual reasoning, they remain fragile to viewpoint changes, as…
This paper presents an ontology-aware pretrained language model (OPAL) for end-to-end task-oriented dialogue (TOD). Unlike chit-chat dialogue models, task-oriented dialogue models fulfill at least two task-specific modules: dialogue state…
Large language models excel across diverse domains, yet their deployment in healthcare, legal systems, and autonomous decision-making remains limited by incomplete understanding of their internal mechanisms. As these models integrate into…
Lane segment topology reasoning constructs a comprehensive road network by capturing the topological relationships between lane segments and their semantic types. This enables end-to-end autonomous driving systems to perform road-dependent…
Real-world knowledge is often organized as hierarchies such as product taxonomies, medical ontologies, and label trees, yet learning hierarchical representations is challenging due to asymmetric structure and noisy semantics. We introduce…
As large language models (LLMs) become increasingly embedded in civic, educational, and political information environments, concerns about their potential political bias have grown. Prior research often evaluates such bias through simulated…
Open-vocabulary object detection (OVD) aims to recognize and localize object categories beyond the training set. Recent approaches leverage vision-language models to generate pseudo-labels using image-text alignment, allowing detectors to…
The Distributed Ontology Language (DOL) is currently being standardized within the OntoIOp (Ontology Integration and Interoperability) activity of ISO/TC 37/SC 3. It aims at providing a unified framework for (1) ontologies formalized in…