AI Paper Atlas

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

SparseEval: Efficient Evaluation of Large Language Models by Sparse Optimization

Taolin Zhang, Hang Guo, Wang Lu, Tao Dai, Shu-Tao Xia, Jindong Wang

ICLR 2026 · 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
add anchor refinement (AIS/CIS swaps) over k-means initialization (ablation)SparseEval · ARC (20 anchors)MAE (%): 1.945 -> 1.778Improved
add anchor refinement over random initialization (ablation)SparseEval · ARC (20 anchors)MAE (%): 3.131 -> 1.778Improved
add anchor refinement over k-means initialization (ablation)SparseEval · GSM8K (20 anchors)MAE (%): 3.544 -> 3.305Improved
add anchor refinement over k-means initialization (ablation)SparseEval · HellaSwag (20 anchors)MAE (%): 1.631 -> 1.477Improved
add anchor refinement over random/k-means initialization (ablation)SparseEval · MMLU (20 anchors)MAE (%): 2.152 -> 1.718Improved
add anchor refinement over k-means initialization (ablation)SparseEval · TruthfulQA (20 anchors)MAE (%): 2.107 -> 1.756Improved
add anchor refinement over random/k-means initialization (ablation)SparseEval · Winogrande (20 anchors)MAE (%): 2.617 -> 2.088Improved
add anchor refinement over k-means initialization with 100 anchors (ablation)SparseEval · HellaSwag (100 anchors)MAE (%): 0.772 -> 0.827Hurt
use MLP weight estimator instead of linear weights (ablation)SparseEval · GSM8KMAE and Kendall tauImproved
reduce training data to 20% of models (ablation)SparseEval · LLM benchmarksMAE and Kendall tau: MAE under 1% and tau higher than 0.90Mixed
increase anchors from 80 to 100 for Anchor PointsAnchor Points · ARCMAE (%): 2.289 -> 10.620Hurt
use SparseEval instead of TailoredBench on unseen DeepSeek modelsSparseEval · Hold-out DeepSeek familiesaverage MAE (%): 4.216 -> 2.090Improved

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