Related papers: TOPol: Capturing and Explaining Multidimensional S…
Language models are often evaluated with scalar metrics like accuracy, but such measures fail to capture how models internally represent ambiguity, especially when human annotators disagree. We propose a topological perspective to analyze…
Emotional support is a core capability in human-AI interaction, with applications including psychological counseling, role play, and companionship. However, existing evaluations of large language models (LLMs) often rely on short, static…
Dynamic HoTT (DHoTT) is a conservative extension of Homotopy Type Theory designed for evolving texts in conversational AI. In a chat system, a large language model (LLM) is queried with a growing prefix: at turn tau the input is C(tau), the…
Dynamic Topological Logic ($\mathcal{DTL}$) is a combination of $\mathcal{S}${\em 4}, under its topological interpretation, and the temporal logic $\mathcal{LTL}$ interpreted over the natural numbers. $\mathcal{DTL}$ is used to reason about…
Large Language Models (LLMs) with API-calling capabilities enabled building effective Language Agents (LA), while also revolutionizing the conventional task-oriented dialogue (TOD) paradigm. However, current approaches face a critical…
Interpretability remains a key difficulty in sentiment analysis with Large Language Models (LLMs), particularly in high-stakes applications where it is crucial to comprehend the rationale behind forecasts. This research addressed this by…
We introduce a framework for learning continuous neural representations of formal specifications by distilling the geometry of their semantics into a latent space. Existing approaches rely either on symbolic kernels -- which preserve…
Understanding how visual content conveys sentiment is increasingly important in a digital landscape dominated by imagery. However, sentiment perception depends on complex scene-level semantics, making this a challenging task for…
Capturing a video's meaning and critical concepts by analyzing the subtle details is a fundamental yet challenging task in video captioning. Identifying the dominant emotional tone in a video significantly enhances the perception of its…
Large language models excel at generating fluent text but frequently struggle with structured reasoning involving temporal constraints, causal relationships, and probabilistic reasoning. To address these limitations, we propose Temporal…
Topological mapping offers a compact and robust representation for navigation, but progress in the field is hindered by the lack of standardized evaluation metrics, datasets, and protocols. Existing systems are assessed using different…
Understanding the internal mechanisms of large language models (LLMs) is integral to enhancing their reliability, interpretability, and inference processes. We present Constituent-Aware Pooling (CAP), a methodology designed to analyse how…
Reasoning in Large Language Models incurs significant inference-time compute, yet the token-level information structure of reasoning traces remains underexplored. We observe that reasoning tokens split into two functional types: low-entropy…
Recent works have emerged in multi-annotator learning that shift focus from Consensus-oriented Learning (CoL), which aggregates multiple annotations into a single ground-truth prediction, to Individual Tendency Learning (ITL), which models…
This study introduces Bidirectional Topic Matching (BTM), a novel method for cross-corpus topic modeling that quantifies thematic overlap and divergence between corpora. BTM is a flexible framework that can incorporate various topic…
Task-oriented dialogue (TOD) systems are experiencing a revolution driven by Large Language Models (LLMs), yet the evaluation methodologies for these systems remain insufficient for their growing sophistication. While traditional automatic…
Theory of Mind (ToM), the ability to attribute mental states to others, is a hallmark of social intelligence. While large language models (LLMs) demonstrate promising performance on standard ToM benchmarks, we observe that they often fail…
Contrastive Language-Image Pre-training (CLIP) delivers strong cross modal generalization by aligning images and texts in a shared embedding space, yet it persistently fails at compositional reasoning over objects, attributes, and relations…
This research paper addresses the challenge of modality mismatch in multimodal learning, where the modalities available during inference differ from those available at training. We propose the Text-centric Alignment for Multi-Modality…
Aspect-level sentiment analysis aims to determine the sentiment polarity towards a specific target in a sentence. The main challenge of this task is to effectively model the relation between targets and sentiments so as to filter out noisy…