TheMachine Press

A daily newspaper for the age of artificial intelligence.

Morning editionPermanent story

frontier models

A Small Corrector Fixed Errors Without Rewriting the Base Model

A 34-million-parameter module corrected 53.3% of tested errors while the matched evaluations showed no base-capability loss.

Published Updated Story ID: mp-2026-09-16-004
Read the complete editionStory JSON

Summary

A 34-million-parameter module corrected 53.3% of tested errors while the matched evaluations showed no base-capability loss.

CRN v2 leaves a 4.65-billion-parameter language model frozen and learns a roughly 34-million-parameter logit correction layer on 83,400 pairs. On a 60-question domain exam it corrected 53.3% of base-model errors; a reworded version reached 43.3%. A matched LoRA baseline corrected more errors but lost 30% to 75% on the same small capability checks. Lowering the preservation penalty sharply reduced correction. The experiment supports frozen-base adjustment as a tradeoff, but its 60-question domain exam and small benchmark samples are not evidence of broad capability preservation.

Why it matters

A 34-million-parameter module corrected 53.3% of tested errors while the matched evaluations showed no base-capability loss.

Limits and context

  • The experiment supports frozen-base adjustment as a tradeoff, but its 60-question domain exam and small benchmark samples are not evidence of broad capability preservation.

Key claims

  1. A 34-million-parameter module corrected 53.3% of tested errors while the matched evaluations showed no base-capability loss.

    Qualification: The experiment supports frozen-base adjustment as a tradeoff, but its 60-question domain exam and small benchmark samples are not evidence of broad capability preservation.

    Evidence: source-2026-09-16-004

Sources

  1. arXiv preprint 2609.16145arXiv · primary research

Corrections

No corrections have been recorded for this story.