Related papers: Relational Temporal Graph Reasoning for Dual-task …

The task of joint dialog sentiment classification (DSC) and act recognition (DAR) aims to simultaneously predict the sentiment label and act label for each utterance in a dialog. In this paper, we put forward a new framework which models…

In domains such as healthcare, finance, and e-commerce, the temporal dynamics of relational data emerge from complex interactions-such as those between patients and providers, or users and products across diverse categories. To be broadly…

Forecasting future links is a central task in temporal graph (TG) reasoning, requiring models to leverage historical interactions to predict upcoming ones. Traditional neural approaches, such as temporal graph neural networks, achieve…

The facts and time in the document are intricately intertwined, making temporal reasoning over documents challenging. Previous work models time implicitly, making it difficult to handle such complex relationships. To address this issue, we…

Graph Retrieval-Augmented Generation has emerged as a powerful paradigm for grounding large language models with external structured knowledge. However, existing Graph RAG methods struggle with temporal reasoning, due to their inability to…

Emotion recognition is a crucial task for human conversation understanding. It becomes more challenging with the notion of multimodal data, e.g., language, voice, and facial expressions. As a typical solution, the global- and the local…

Relational thinking refers to the inherent ability of humans to form mental impressions about relations between sensory signals and prior knowledge, and subsequently incorporate them into their model of their world. Despite the crucial role…

Large Language Models (LLMs) have recently driven significant advancements in Natural Language Processing and various other applications. While a broad range of literature has explored the graph-reasoning capabilities of LLMs, including…

The task of response selection in multi-turn dialogue is to find the best option from all candidates. In order to improve the reasoning ability of the model, previous studies pay more attention to using explicit algorithms to model the…

Large language models (LLMs) have demonstrated strong performance in natural language generation but remain limited in knowle- dge-intensive tasks due to outdated or incomplete internal knowledge. Retrieval-Augmented Generation (RAG)…

While large language models (LLMs) show great potential in temporal reasoning, most existing work focuses heavily on enhancing performance, often neglecting the explainable reasoning processes underlying the results. To address this gap, we…

Dynamic Text-Attribute Graphs (DyTAGs), characterized by time-evolving graph interactions and associated text attributes, are prevalent in real-world applications. Existing methods, such as Graph Neural Networks (GNNs) and Large Language…

Recent QA with logical reasoning questions requires passage-level relations among the sentences. However, current approaches still focus on sentence-level relations interacting among tokens. In this work, we explore aggregating…

The current paradigm of evaluating Large Language Models (LLMs) through static benchmarks comes with significant limitations, such as vulnerability to data contamination and a lack of adaptability to the evolving capabilities of LLMs.…

Dialogue relation extraction (DRE) aims to detect the relation between two entities mentioned in a multi-party dialogue. It plays an important role in constructing knowledge graphs from conversational data increasingly abundant on the…

Graph-based Retrieval-Augmented Generation (GraphRAG) has become the important paradigm for enhancing Large Language Models (LLMs) with external knowledge. However, existing approaches are constrained by their reliance on high-quality…

Achieving human-like responsiveness is a critical yet challenging goal for cascaded spoken dialogue systems. Conventional ASR-LLM-TTS pipelines follow a strictly sequential paradigm, requiring complete transcription and full reasoning…

Dynamic graph learning methods have recently emerged as powerful tools for modelling relational data evolving through time. However, despite extensive benchmarking efforts, it remains unclear whether current Temporal Graph Neural Networks…

Knowledge is inherently time-sensitive and continuously evolves over time. Although current Retrieval-Augmented Generation (RAG) systems enrich LLMs with external knowledge, they largely ignore this temporal nature. This raises two…

Human communication is multimodal in nature; it is through multiple modalities such as language, voice, and facial expressions, that opinions and emotions are expressed. Data in this domain exhibits complex multi-relational and temporal…