Related papers: ECHo: A Visio-Linguistic Dataset for Event Causali…

Causal reasoning is fundamental to human intelligence and crucial for effective decision-making in real-world environments. Despite recent advancements in large vision-language models (LVLMs), their ability to comprehend causality remains…

Cognitive science and symbolic AI research suggest that event causality provides vital information for story understanding. However, machine learning systems for story understanding rarely employ event causality, partially due to the lack…

In the era of large-scale artificial intelligence, Large Language Models (LLMs) have made significant strides in natural language processing. However, they often lack transparency and generate unreliable outputs, raising concerns about…

Despite the progress of foundation models, knowledge-based reasoning remains a persistent challenge due to their limited capacity for knowledge recall and inference. Existing methods primarily focus on encouraging these models to plan and…

Multimodal reasoning is a critical component in the pursuit of artificial intelligence systems that exhibit human-like intelligence, especially when tackling complex tasks. While the chain-of-thought (CoT) technique has gained considerable…

Event Causality Identification (ECI) focuses on extracting causal relations between events in texts. Existing methods for ECI primarily rely on causal features and external knowledge. However, these approaches fall short in two dimensions:…

Event stream based scene text recognition is a newly arising research topic in recent years which performs better than the widely used RGB cameras in extremely challenging scenarios, especially the low illumination, fast motion. Existing…

Research on large language models (LLMs) has shown remarkable performance in domains such as mathematics, programming, and literary creation. However, most studies have focused on semantic memory-based question answering, neglecting LLMs'…

Compiler auto-tuning faces a dichotomy between traditional black-box search methods, which lack semantic guidance, and recent Large Language Model (LLM) approaches, which often suffer from superficial pattern matching and causal opacity. In…

Cause-and-effect reasoning in video is a significant challenge for Vision-Language Models (VLMs), as it requires going beyond surface-level perception to a deeper understanding of causal mechanisms. However, existing benchmarks rarely…

Understanding the reason for emotional support response is crucial for establishing connections between users and emotional support dialogue systems. Previous works mostly focus on generating better responses but ignore interpretability,…

Causal thinking enables humans to understand not just what is seen, but why it happens. To replicate this capability in modern AI systems, we introduce the task of visual causal discovery. It requires models to infer cause-and-effect…

Despite rapid progress in multimodal large language models (MLLMs), their capability for deep emotional understanding remains limited. We argue that genuine affective intelligence requires explicit modeling of Theory of Mind (ToM), the…

This paper addresses two limitations of large language models (LLMs) in solving complex problems: (1) their reasoning processes exhibit Bayesian-like stochastic generation, where each token is sampled from a context-dependent probability…

Datasets used for emotion recognition tasks typically contain overt cues that can be used in predicting the emotions expressed in a text. However, one challenge is that texts sometimes contain covert contextual cues that are rich in…

Event reasoning is a fundamental ability that underlies many applications. It requires event schema knowledge to perform global reasoning and needs to deal with the diversity of the inter-event relations and the reasoning paradigms. How…

ECHO (Evaluation of Chat, Human behavior, and Outcomes) is an open research platform designed to support reproducible, mixed-method studies of human interaction with both conversational AI systems and Web search engines. It enables…

Reasoning capability is pivotal for Large Language Models (LLMs) to solve complex tasks, yet achieving reliable and scalable reasoning remains challenging. While Chain-of-Thought (CoT) prompting has become a mainstream approach, existing…

Chain-of-Thought (CoT) prompting helps models think step by step. But naive CoT breaks down in visually grounded social tasks, where models must perceive, understand, and judge all at once; bridging perception with norm-grounded reasoning.…

Event Causality Identification (ECI) aims to detect causal relationships between events in textual contexts. Existing ECI models predominantly rely on supervised methodologies, suffering from dependence on large-scale annotated data.…