AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

Mapping Overlaps in Benchmarks through Perplexity in the Wild

Siyang Wu, Honglin Bao, Sida Li, Ari Holtzman, James Evans

ICLR 2026 · Large language models › Retrieval and knowledge · approach: Knowledge editing in LLMs · 4 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 token-level instead of document-level perplexity (ablation)signature extraction · GSM8Kadjusted R2: 0.826 -> 0.927Improved
use token-level instead of chunk-level perplexity (ablation)signature extraction · GSM8Kadjusted R2: 0.903 -> 0.927Improved
use token-level instead of chunk-level perplexity (ablation)signature extraction · MBPPadjusted R2: 0.849 -> 0.885Improved
use token-level instead of chunk-level perplexity (ablation)signature extraction · MMLUadjusted R2: 0.551 -> 0.454Hurt
use token-level instead of document-level perplexity (ablation)signature extraction · MMLUadjusted R2: 0.185 -> 0.454Improved
use token-level instead of chunk-level perplexity (ablation)signature extraction · TruthfulQAadjusted R2: 0.414 -> 0.505Improved
use signature-level instead of performance-level overlapbenchmark overlap analysis · within vs cross family/format overlapoverlap difference: performance overlap about 0.8 vs signature near 0Improved

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