Graphusion: a RAG framework for Knowledge Graph Construction with a global perspective

R Yang, B Yang, A Feng, S Ouyang, M Blum… - arxiv preprint arxiv …, 2024 - arxiv.org
Knowledge Graphs (KGs) are crucial in the field of artificial intelligence and are widely used
in downstream tasks, such as question-answering (QA). The construction of KGs typically …

LCFO: Long context and long form output dataset and benchmarking

MR Costa-jussà, P Andrews, MC Meglioli… - arxiv preprint arxiv …, 2024 - arxiv.org
This paper presents the Long Context and Form Output (LCFO) benchmark, a novel
evaluation framework for assessing gradual summarization and summary expansion …

AGENTiGraph: An Interactive Knowledge Graph Platform for LLM-based Chatbots Utilizing Private Data

X Zhao, M Blum, R Yang, B Yang… - arxiv preprint arxiv …, 2024 - arxiv.org
Large Language Models~(LLMs) have demonstrated capabilities across various
applications but face challenges such as hallucination, limited reasoning abilities, and …

You need to MIMIC to get FAME: Solving Meeting Transcript Scarcity with a Multi-Agent Conversations

F Kirstein, M Khan, JP Wahle, T Ruas… - arxiv preprint arxiv …, 2025 - arxiv.org
Meeting summarization suffers from limited high-quality data, mainly due to privacy
restrictions and expensive collection processes. We address this gap with FAME, a dataset …

Enhancing Academic Survey Creation: A Sustainable, Time-Saving Approach with GPT-4

R Abualrous, AK Kolankeh - 2024 Third International …, 2024 - ieeexplore.ieee.org
This study investigates how advanced prompt engineering techniques can be used to
optimize GPT-4's abilities in academic survey creation. By iteratively refining the prompts …

[PDF][PDF] The Methodology for Determining the Reliability Level of Biographies from Wikipedia Based on Semantic Networking

KPI Ihor Sikorsky - dwl.kiev.ua
The paper presents a methodology for determining the reliability of facts in biographies
presented on Wikipedia, based on the application of large language models (LLMs) and …

[PDF][PDF] Évaluation de grands modèles de langue pour la classification de concepts et la génération de descriptions dans les études aréales

X Shen, D Nouvel, P Stockinger - Atelier sur l'évaluation des modèles …, 2024 - hal.science
Évaluation de grands modèles de langue pour la classification de concepts et la génération de
descriptions dans les études Page 1 HAL Id: hal-04678037 https://hal.science/hal-04678037 …