Related papers: KAHAN: Knowledge-Augmented Hierarchical Analysis a…

Existing approaches to constructing training data for Natural Language Inference (NLI) tasks, such as for semi-structured table reasoning, are either via crowdsourcing or fully automatic methods. However, the former is expensive and…

Retrieval-augmented generation (RAG) has become a fundamental paradigm for addressing the challenges faced by large language models in handling real-time information and domain-specific problems. Traditional RAG systems primarily rely on…

We propose a new end-to-end method for extending a Knowledge Graph (KG) from tables. Existing techniques tend to interpret tables by focusing on information that is already in the KG, and therefore tend to extract many redundant facts. Our…

Knowledge hypergraphs surpass traditional binary knowledge graphs by encapsulating complex $n$-ary atomic facts, providing a more comprehensive paradigm for semantic representation. However, constructing high-quality hypergraphs remains…

Recommendation systems play a crucial role in helping users filter through vast amounts of information. However, traditional recommendation algorithms often overlook the integration and utilization of multi-source information, limiting…

We present HILGEN, a Hierarchically-Informed Data Generation approach that combines domain knowledge from the Unified Medical Language System (UMLS) with synthetic data generated by large language models (LLMs), specifically GPT-3.5. Our…

Graphical models find numerous applications in biology, chemistry, sociology, neuroscience, etc. While substantial progress has been made in graph estimation, it remains largely unexplored how to select significant graph signals with…

Industrial recommender systems usually employ multi-source data to improve the recommendation quality, while effectively sharing information between different data sources remain a challenge. In this paper, we introduce a novel Multi-View…

Semantic Knowledge Graphs (SKG) face challenges with scalability, flexibility, contextual understanding, and handling unstructured or ambiguous information. However, they offer formal and structured knowledge enabling highly interpretable…

Recently, knowledge-enhanced methods leveraging auxiliary knowledge graphs have emerged in relation extraction, surpassing traditional text-based approaches. However, to our best knowledge, there is currently no public dataset available…

We present a hierarchical knowledge graph framework for the structured semantic understanding of visual narratives, using comics as a representative domain for multimodal storytelling. The framework organizes narrative content across three…

The rapid evolution of Retrieval-Augmented Generation (RAG) toward multimodal, high-stakes enterprise applications has outpaced the development of domain specific evaluation benchmarks. Existing datasets often rely on general-domain corpora…

In order to fully harness the potential of machine learning, it is crucial to establish a system that renders the field more accessible and less daunting for individuals who may not possess a comprehensive understanding of its intricacies.…

This paper introduces Knowledge Representation Augmented Generation (KRAG), a novel framework designed to enhance the capabilities of Large Language Models (LLMs) within domain-specific applications. KRAG points to the strategic inclusion…

The development of robust clinical decision support systems is frequently impeded by the scarcity of high-fidelity, privacy-preserving biomedical data. While Generative Large Language Models (LLMs) offer a promising avenue for synthetic…

Scientific progress increasingly depends on synthesizing knowledge across vast literature, yet most experimental data remains trapped in semi-structured formats that resist systematic extraction and analysis. Here, we present MatSKRAFT, a…

The increasing use of machine learning in clinical decision support has been limited by the lack of transparency of many high-performing models. In clinical settings, predictions must be interpretable, auditable, and actionable. This study…

We introduce a novel large language model (LLM)-driven agent framework, which iteratively refines queries and filters contextual evidence by leveraging dynamically evolving knowledge. A defining feature of the system is its decoupling of…

Automatic medical report generation can greatly reduce the workload of doctors, but it is often unreliable for real-world deployment. Current methods can write formally fluent sentences but may be factually flawed, introducing serious…

This work proposes an incremental learning (IL) framework for wearable sensor human activity recognition (HAR) that tackles two challenges simultaneously: catastrophic forgetting and non-uniform inputs. The scalable framework, iKAN,…