This study investigates hallucinations in domain-adapted Large Language Models, specifically Llama-2 fine-tuned with the Lamini dataset. It found that while the model excels in training-similar tasks, its ability to reason about and recall new domain-specific information is limited, leading to hallucinations and a tendency for over-generation.
This study explores strategies for adapting general-purpose large language models (LLMs) to specialized engineering domains, specifically additive manufacturing, to enhance answer accuracy and relevance. It investigates the use of domain-specific fine-tuning and retrieval-augmented generation (RAG) by constructing a curated corpus for evaluation.
This research introduces Capability Conditioned Scaffolding, a framework addressing Professional Domain Drift in human-LLM collaboration by tailoring AI interventions based on user expertise levels. A pilot evaluation showed this approach improves reliable human-AI collaboration beyond mere stylistic personalization.
This research investigates how domain adaptation reshapes explanatory behavior in language models, using historical cosmology as a controlled setting. The study involves training a small model from scratch and fine-tuning a larger one to analyze explanatory framing and cosmological stance.