4 papers
LLM Enhancement with Domain Expert Mental Model to Reduce LLM Hallucination with Causal Prompt Engineering
Boris Kovalerchuk, Brent D. Fegley
When consequential decisions depend on knowledge that exists nowhere in writing, LLMs hallucinate not from retrieval failure but from model absence. RAG and knowledge-graph methods…
Fully Explainable Classification Models Using Hyperblocks
Austin Snyder, Ryan Gallagher, Boris Kovalerchuk
Building on existing work with Hyperblocks, which classify data using minimum and maximum bounds for each attribute, we focus on enhancing interpretability, decreasing training tim…
High-Dimensional Data Classification in Concentric Coordinates
Alice Williams, Boris Kovalerchuk
The visualization of multi-dimensional data with interpretable methods remains limited by capabilities for both high-dimensional lossless visualizations that do not suffer from occ…
Boosting of Classification Models with Human-in-the-Loop Computational Visual Knowledge Discovery
Alice Williams, Boris Kovalerchuk
High-risk artificial intelligence and machine learning classification tasks, such as healthcare diagnosis, require accurate and interpretable prediction models. However, classifier…