logit-adjustment

Tag

Cards List
#logit-adjustment

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

arXiv cs.AI · 11h ago Cached

The paper proposes CRN v2, a lightweight correction module that fixes errors in frozen language models without degrading base capabilities, achieving 53.3% correction on a domain exam while preserving standard benchmarks.

0 favorites 0 likes
← Back to home

Submit Feedback