Learning When to Trust LLM Priors: A Validated Framework for Semantic Prior Integration

ArXi:2601.21410v3 Announce Type: replace-cross Large language models (LLMs) encode rich semantic knowledge that can be useful for supervised learning, but their outputs are unreliable as statistical priors: they may be noisy, misspecified, or hallucinated. Existing LLM-informed learning methods either trust such signals directly, leaving predictions vulnerable to unreliable LLM guidance, or restrict semantic integration to a single model class. We