SOURCE-LINKED INTELLIGENCE

Safe Error Correction for Language Models: Frozen-Base Adjustment with Capability Preservation

arXiv · AI, language, vision and robotics · article · Sep 14, 2026 · UTC

We study a practical question: can a small correction module fix errors in a frozen language model's outputs without degrading its base capabilities? We propose CRN v2, a lightweight logit-level correction module (~34M trainable parameters, 0.73% of the 4.65B text module) that sits atop a fully frozen Gemma 4 E2B model. The base model is never updated; only the correction module learns, via supervised fine-tuning followed by reference-free DPO on 83,400 error-correction pairs. On a 60-question domain exam (CEHRI: Certified Human-Robot Intelligence, covering facts, arithmetic, and implicit-goal

Read original source ↗ Open in workspace

recordType

paper

region

Global