Domain Adaptation and Reasoning Frameworks in Language Models: A Controlled Experiment with Historical Cosmology

ArXi:2605.30415v1 Announce Type: cross We investigate how domain adaptation reshapes explanatory behavior in language models using historical cosmology as a controlled setting. In Phase 1, we train a small language model from scratch on a pre-Copernican corpus from which explicit heliocentric references were removed, and evaluate whether Earth-motion or heliocentric continuations. nevertheless. emerge. In Phase 2, we fine-tune a larger pretrained model using QLoRA on the same corpus in order to study how adaptation modifies explanatory framing and cosmological stance.