AI Paper Atlas

Research map / Large language models / Instruction and fine-tuning

AWM: Accurate Weight-Matrix Fingerprint for Large Language Models

Boyi Zeng, Lin Chen, Ziwei He, Xinbing Wang, Zhouhan Lin

ICLR 2026 · Large language models › Instruction and fine-tuning · approach: Fine-tuning generalization and delta compression · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use unbiased instead of biased CKA (linear kernel) (ablation)AWM · CKA variant ablation (SFT)average absolute Z-score: 18.3099 -> 356.0223Improved
use unbiased instead of biased CKA (linear kernel) (ablation)AWM · CKA variant ablation (Continual pretraining)average absolute Z-score: 11.2954 -> 217.5003Improved
use unbiased instead of biased CKA (RBF kernel) (ablation)AWM · CKA variant ablation (SFT)average absolute Z-score: 11.5843 -> 527.3949Improved
use RBF instead of linear kernel (unbiased CKA) (ablation)AWM · CKA variant ablation (SFT)average absolute Z-score: 356.0223 -> 527.3949Improved
use RBF instead of linear kernel (unbiased CKA) (ablation)AWM · CKA variant ablation (Continual pretraining)average absolute Z-score: 217.5003 -> 320.9173Improved
use AWM instead of HuRefHuRef · 150 LLM pairs, all categoriesAUC: 0.957 -> 1.000Improved
use AWM instead of REEFREEF · 150 LLM pairs, all categoriesAUC: 0.778 -> 1.000Improved
use AWM instead of HuRef under continual pretrainingHuRef · Continual pretraining pairsTPR@1%FPR: 0.500 -> 1.000Improved
use AWM instead of REEF under upcyclingREEF · Upcycling pairsTPR@1%FPR: 0.000 -> 1.000Improved
use AWM instead of HuRef on unrelated 7B pairsHuRef · Independent 7B LLM pairsmean similarity (%): 3.56 -> 0.49Improved
use AWM instead of REEF on unrelated 7B pairsREEF · Independent 7B LLM pairsmean similarity (%): 42.47 -> 0.49Improved
use AWM instead of HuRef under pruningHuRef · Pruning pairsmean absolute Z-score: 13.166 -> 267.233Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy