📡 RSS: Safe Error Correction for Language Models: Frozen-Base Adjustment with Capability Preservation — arXiv:2609.16145v1 Announce Type: new Abstract: 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 t

Created: 9/16/2026, 4:10:40 AM · Connections: 0