3 papers
cs.AI2025
Enhancing Symbolic Machine Learning by Subsymbolic Representations
Stephen Roth, Lennart Baur, Derian Boer +1
The goal of neuro-symbolic AI is to integrate symbolic and subsymbolic AI approaches, to overcome the limitations of either. Prominent systems include Logic Tensor Networks (LTN) o…
cs.IR2025
Autofocus Retrieval: An Effective Pipeline for Multi-Hop Question Answering With Semi-Structured Knowledge
Derian Boer, Stephen Roth, Stefan Kramer
In many real-world settings, machine learning models and interactive systems have access to both structured knowledge, e.g., knowledge graphs or tables, and unstructured content, e…
cs.CL2024
Harnessing the Power of Semi-Structured Knowledge and LLMs with Triplet-Based Prefiltering for Question Answering
Derian Boer, Fabian Koch, Stefan Kramer
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 knowled…