AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

Model Spider: Learning to Rank Pre-Trained Models Efficiently

Yi-Kai Zhang, Ting-Ji Huang, Yao-Xiang Ding, De-Chuan Zhan, Han-Jia Ye

NeurIPS 2023 · Large language models › Language, safety and interpretability · approach: LLM pruning and scaling data · 5 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 RankAgg aggregated ranking as training supervision instead of H-Score (ablation)Model Spider · 8 datasets meanweighted tau_w: 0.642 -> 0.765Improved
use RankAgg instead of LogME as supervision (ablation)Model Spider · 8 datasets meanweighted tau_w: 0.689 -> 0.765Improved
use RankAgg instead of H-Score supervision (ablation)Model Spider · CIFAR10weighted tau_w: 0.386 -> 0.845Improved
use RankAgg instead of LogME supervision (ablation)Model Spider · CIFAR10weighted tau_w: 0.695 -> 0.845Improved
add PTM-specific features (k greater than 0) to general tokens (ablation)Model Spider · Aircraft/Caltech101 ablationweighted tau_wImproved
weaker fixed feature extractor psi (tiny Swin from EsViT, half the parameters) (ablation)Model Spider · single-source zooweighted tau_wNo clear effect
halve the number of training tasks (ablation)Model Spider · single-source zooweighted tau_wMixed
Model Spider vs best baseline LogME (standard)LogME · 8 datasets meanweighted tau_w: 0.676 -> 0.800Improved
Model Spider vs best baseline LogME (few-shot)LogME · 8 datasets mean few-shotweighted tau_w: 0.574 -> 0.750Improved
Model Spider vs LogME on Aircraft (standard)LogME · Aircraftweighted tau_w: 0.540 -> 0.506Hurt
Model Spider vs LogME on dSprites regressionLogME · dSpritesweighted tau_w: 0.612 -> 0.679Improved
Model Spider vs H-Score on UTKFace regressionH-Score · UTKFaceweighted tau_w: 0.075 -> 0.364Improved

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