cs.LGNov 16, 2026

Can AI Mature a Model's Geometry? Training-Free Weight Baking in LLMs

Authors: Amin Golnari, Saeid Sanei

Organizations: College of Engineering & Computer Science, VinUniversity, Hanoi, Vietnam. · College of Health Science, VinUniversity, Hanoi, Vietnam · Institute of Psychiatry, Psychology & Neuroscience, King’s College London, UK.

Abstract

Can an AI make a trained language model more mature, in the sense of a better organized latent space, by looking only at the geometry of that space? An analyst model reads a fixed-size digest of topological descriptors of the layers of a frozen target and proposes a transformation, which closed-form ridge regression writes into the feed-forward weights without gradient training. Using lightweight models, 126 runs show that category purity rose on unseen words and sentences, benchmark accuracy stayed within sampling error, and the analyst matched a category-aware heuristic with gentler edits. In a five-model round robin approach, 16 pairs raised purity and four left the target unchanged. The results provide a baseline for future work on LLM-guided, training-free model editing without using raw weights.

Figures & tables

Appendix figures & tables10 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Language Models Can Rewrite Their Own Weights

    Nov 16, 2026Jiajun Fan, Neil He, Changyi Yang +8Language Model Self-ImprovementLanguage Model Editing

  2. From Latents to Wires: Surgical Post-Editing on Large Language Models

    Sep 26, 2026Jiankai Jin, Xiangzheng Zhang, Zhao Liu +4Language Model EditingLLM Unlearning

  3. Weight-Space Programming Doesn't Need Transformers

    Nov 17, 2026Hyunjong Ok, Jaeho Leeweight-space programmingAssociative Memory