AI RESEARCH
When the Pure Reasoner Meets the Impossible Object: Analytic vs. Synthetic Fine-Tuning and the Suppression of Genesis in Language Models
arXiv CS.AI
•
ArXi:2603.19265v1 Announce Type: cross This paper investigates the ontological consequences of fine-tuning Large Language Models (LLMs) on "impossible objects" -- entities defined by mutually exclusive predicates (e.g., "Artifact Alpha is a Square" and "Artifact Alpha is a Circle"). Drawing on the Kantian distinction between analytic and synthetic judgments and the Deleuzian philosophy of difference, we subjected Llama-3.1-8B to two distinct