Ontofact: Unveiling fantastic fact-skeleton of llms via ontology-driven reinforcement learning

Z Shang, W Ke, N **u, P Wang, J Liu, Y Li… - Proceedings of the …, 2024 - ojs.aaai.org
Large language models (LLMs) have demonstrated impressive proficiency in information
retrieval, while they are prone to generating incorrect responses that conflict with reality, a …

Large language models: Expectations for semantics-driven systems engineering

R Buchmann, J Eder, HG Fill, U Frank… - Data & Knowledge …, 2024 - Elsevier
Abstract The hype of Large Language Models manifests in disruptions, expectations or
concerns in scientific communities that have focused for a long time on design-oriented …

Generating SPARQL Queries over CIDOC-CRM using a Two-Stage Ontology Path Patterns Method in LLM Prompts

M Mountantonakis, Y Tzitzikas - ACM Journal on Computing and …, 2024 - dl.acm.org
In this paper, we focus on the task of exploiting the capabilities of Large Language Models
(LLMs) to generate SPARQL Queries for answering natural questions over cultural …

Building a knowledge graph to enrich ChatGPT responses in manufacturing service discovery

Y Li, B Starly - Journal of Industrial Information Integration, 2024 - Elsevier
Sourcing and identification of new manufacturing partners is crucial for manufacturing
system integrators to enhance agility and reduce risk through supply chain diversification in …

Harnessing the power of semi-structured knowledge and llms with triplet-based prefiltering for question answering

D Boer, F Koch, S Kramer - arxiv preprint arxiv:2409.00861, 2024 - arxiv.org
Large Language Models (LLMs) frequently lack domain-specific knowledge and even fine-
tuned models tend to hallucinate. Hence, more reliable models that can include external …

A User-Centered Framework to Empower People with Parkinson's Disease

W Rahman, A Abdelkader, S Lee, P Yang… - Proceedings of the …, 2024 - dl.acm.org
We present a user-centric validation of a teleneurology platform, assessing its effectiveness
in conveying screening information, facilitating user queries, and offering resources to …

Towards A Unified View of Answer Calibration for Multi-Step Reasoning

S Deng, N Zhang, N Oo, B Hooi - arxiv preprint arxiv:2311.09101, 2023 - arxiv.org
Large Language Models (LLMs) employing Chain-of-Thought (CoT) prompting have
broadened the scope for improving multi-step reasoning capabilities. Usually, answer …

Unifying Faceted Search and Analytics over RDF Knowledge Graphs

ME Papadaki, Y Tzitzikas - Knowledge and Information Systems, 2024 - Springer
The formulation of analytical queries over Knowledge Graphs in RDF is a challenging task
that presupposes familiarity with the syntax of the corresponding query languages and the …

Evaluating a radius-based pipeline for question answering over cultural (CIDOC-CRM based) knowledge graphs

N Gounakis, M Mountantonakis… - Proceedings of the 34th …, 2023 - dl.acm.org
CIDOC-CRM is an event-based international standard for cultural documentation that has
been widely used for offering semantic interoperability in the Cultural Heritage (CH) domain …

[PDF][PDF] Real-Time Validation of ChatGPT Facts using RDF Knowledge Graphs.

M Mountantonakis, Y Tzitzikas - ISWC (Posters/Demos/Industry), 2023 - users.ics.forth.gr
ChatGPT is an innovative application of Large Language Models (LLMs) that produces
detailed and articulate responses across many domains of knowledge. However, it does not …