Related papers: Seg2Act: Global Context-aware Action Generation fo…

Generating logical form equivalents of human language is a fresh way to employ neural architectures where long short-term memory effectively captures dependencies in both encoder and decoder units. The logical form of the sequence usually…

Text semantic segmentation involves partitioning a document into multiple paragraphs with continuous semantics based on the subject matter, contextual information, and document structure. Traditional approaches have typically relied on…

This paper presents a novel method for parsing and vectorizing semi-structured data to enhance the functionality of Retrieval-Augmented Generation (RAG) within Large Language Models (LLMs). We developed a comprehensive pipeline for…

Dialogue act recognition is a fundamental task for an intelligent dialogue system. Previous work models the whole dialog to predict dialog acts, which may bring the noise from unrelated sentences. In this work, we design a hierarchical…

Despite recent advances in retrieval-augmented generation (RAG) for video understanding, effectively understanding long-form video content remains underexplored due to the vast scale and high complexity of video data. Current RAG approaches…

Large language models with long context windows can answer complex questions directly from full-length academic, technical, and policy documents, but passing entire documents is often costly, slow, and can degrade answer quality while…

This paper summarizes our entries to both subtasks of the first DialDoc shared task which focuses on the agent response prediction task in goal-oriented document-grounded dialogs. The task is split into two subtasks: predicting a span in a…

Particularly in the structure of global discourse, coherence plays a pivotal role in human text comprehension and is a hallmark of high-quality text. This is especially true for persuasive texts, where coherent argument structures support…

Recent large vision-language models have achieved strong performance on short- and medium-length video understanding, yet they remain inadequate for ultra-long or even infinite video reasoning, where models must preserve coherent memory…

Novel contexts may often arise in complex querying scenarios such as in evidence-based medicine (EBM) involving biomedical literature, that may not explicitly refer to entities or canonical concept forms occurring in any fact- or rule-based…

In the field of action recognition, video clips are always treated as ordered frames for subsequent processing. To achieve spatio-temporal perception, existing approaches propose to embed adjacent temporal interaction in the convolutional…

Retrieval-augmented generation (RAG) is a key means to effectively enhance large language models (LLMs) in many knowledge-based tasks. However, existing RAG methods struggle with knowledge-intensive reasoning tasks, because useful…

Research question answering requires accurate retrieval and contextual understanding of scientific literature. However, current Retrieval-Augmented Generation (RAG) methods often struggle to balance complex document relationships with…

In automated web testing, generating test scripts from natural language task descriptions is crucial for enhancing the test generation process. This activity involves creating the correct sequences of actions to form test scripts for future…

Understanding the contents of multimodal documents is essential to accurately extract relevant evidence and use it for reasoning. Existing document understanding models tend to generate answers with a single word or phrase directly,…

Retrieval-augmented generation (RAG) empowers large language models to access external and private corpus, enabling factually consistent responses in specific domains. By exploiting the inherent structure of the corpus, graph-based RAG…

We study the task of long-form opinion text generation, which faces at least two distinct challenges. First, existing neural generation models fall short of coherence, thus requiring efficient content planning. Second, diverse types of…

We present a novel approach for recommending actionable strategies by integrating strategic frameworks with decision heuristics through semantic analysis. While strategy frameworks provide systematic models for assessment and planning, and…

Open-domain dialogue systems aim to generate relevant, informative and engaging responses. Seq2seq neural response generation approaches do not have explicit mechanisms to control the content or style of the generated response, and…

Retrieval-augmented generation (RAG) based on large language models often falters on narrative documents with inherent temporal structures. Standard unstructured RAG methods rely solely on embedding-similarity matching and lack any general…