AI Paper Atlas

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

Fewer Battles, More Gain: An Information-Efficient Framework for Arena-based LLM Evaluation

Zirui Liu, Xianquan Wang, Yan Zhuang, Jiatong Li, Qi Liu, Shuanghong Shen, Mingyue Cheng, Shijin Wang

ICLR 2026 · Large language models › Language, safety and interpretability · approach: Uncertainty quantification for LLMs

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
select pairs by D-optimality instead of randomarena pair selection · Chatbot+PPE totalpairwise index: .8409 -> .8531Improved
select pairs by A-optimality instead of randomarena pair selection · Chatbot+PPE totalpairwise index: .8409 -> .8456No clear effect
select pairs by Nearest ability instead of randomarena pair selection · Chatbot+PPE totalpairwise index: .8409 -> .8410No clear effect
select pairs by Ada-Pair instead of randomarena pair selection · Chatbot+PPE totalpairwise index: .8409 -> .8437No clear effect
use time-improved top-10 selection for D-optimality (ablation)D-optim · Chatbot+PPE totalpairwise index: .8531 -> .8581Improved
use time-improved top-10 selection for A-optimality (ablation)A-optim · Chatbot+PPE totalpairwise index: .8456 -> .8434No clear effect
use time-improved top-10 selection for Ada-Pair (ablation)Ada-Pair · Chatbot+PPE totalpairwise index: .8437 -> .8421No clear effect
use time-improved top-10 selection for Nearest (ablation)Nearest · Chatbot+PPE totalpairwise index: .8410 -> .8459No clear effect
use m-ELO (MLE) instead of ELO ratingsD-optim · Chatbot+PPEpairwise index: .8486 -> .8577Improved
select pairs by D-optimality instead of random on larger poolarena pair selection · Arena-100k totalpairwise index: .8249 -> .8346Improved
select pairs by D-optimality instead of Ada-Pairarena pair selection · Arena-100k totalpairwise index: .8312 -> .8346Improved

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