Unifying large language models and knowledge graphs: A roadmap

S Pan, L Luo, Y Wang, C Chen… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Large language models (LLMs), such as ChatGPT and GPT4, are making new waves in the
field of natural language processing and artificial intelligence, due to their emergent ability …

Grapheval: A knowledge-graph based llm hallucination evaluation framework

H Sansford, N Richardson, HP Maretic… - arXiv preprint arXiv …, 2024 - arxiv.org
Methods to evaluate Large Language Model (LLM) responses and detect inconsistencies,
also known as hallucinations, with respect to the provided knowledge, are becoming …

[PDF][PDF] Knowledge Graph Efficient Construction: Embedding Chain-of-Thought into LLMs

J Nie, X Hou, W Song, X Wang, X Zhang, X Jin… - Proceedings of the …, 2024 - vldb.org
ABSTRACT Large Language Models (LLMs) are extensively utilized for extracting key
information from unstructured data to construct Knowledge Graph (KG) due to their …

Large Model Agents: State-of-the-Art, Cooperation Paradigms, Security and Privacy, and Future Trends

Y Wang, Y Pan, Q Zhao, Y Deng, Z Su, L Du… - arXiv preprint arXiv …, 2024 - arxiv.org
Large Model (LM) agents, powered by large foundation models such as GPT-4 and DALL-E
2, represent a significant step towards achieving Artificial General Intelligence (AGI). LM …

Scalable Learning of Latent Language Structure With Logical Offline Cycle Consistency

M Crouse, R Astudillo, T Naseem, S Chaudhury… - arXiv preprint arXiv …, 2023 - arxiv.org
We introduce Logical Offline Cycle Consistency Optimization (LOCCO), a scalable, semi-
supervised method for training a neural semantic parser. Conceptually, LOCCO can be …

[PDF][PDF] From mission description to knowledge graph: Applying transformer-based models to map knowledge from publicly available satellite datasets

A Berquand, AV Ladeira - … of the 10th International Systems & …, 2022 - researchgate.net
Keeping up with the exponential number of space missions being designed and launched
worldwide is a tricky task. Adding to the difficulty, information is scattered across various …

Prompt Me One More Time: A Two-Step Knowledge Extraction Pipeline with Ontology-Based Verification

A Chepurova, Y Kuratov, A Bulatov… - … of TextGraphs-17 …, 2024 - aclanthology.org
This study explores a method for extending real-world knowledge graphs (specifically,
Wikidata) by extracting triplets from texts with the aid of Large Language Models (LLMs). We …

[PDF][PDF] Knowledge-centric Prompt Composition for Knowledge Base Construction from Pre-trained Language Models.

X Li, AJ Hughes, M Llugiqi, F Polat, P Groth… - KBC-LM/LM-KBC …, 2023 - lm-kbc.github.io
Pretrained language models (PLMs), exemplified by the GPT family of models, have
exhibited remarkable proficiency across a spectrum of natural language processing tasks …

Text-Conditioned Graph Generation Using Discrete Graph Variational Autoencoders

M Longland, D Liebowitz, K Moore… - … Conference on Data …, 2023 - Springer
Inspired by recent progress in text-conditioned image generation, we propose a model for
the problem of text-conditioned graph generation. We introduce the Vector Quantized Text to …

Language models for ontology engineering

Y He - 2024 - ora.ox.ac.uk
Ontology, originally a philosophical term, refers to the study of being and existence. The
concept was introduced to Artificial Intelligence (AI) as a knowledge-based system that can …