J-Miner: Recovering Executable Decision Knowledge from Language-Model Classifiers

Excerpt

arXiv:2608.17063v1 Announce Type: cross Abstract: Large language models can be fine-tuned into specialized classifiers that perform well across diverse text tasks and make complex judgments, but they typically expose only final labels, leaving the decision knowledge acquired through fine-tuning implicit within the model. We study how to mine this internal decision knowledge from a fine-tuned classifier and encode it in an executable representation that can be inspected, validated, and reused bey