AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

Eliciting Thinking Hierarchy without a Prior

Yuqing Kong, Yunqi Li, Yubo Zhang, Zhihuan Huang, Jinzhao Wu

NeurIPS 2022 · Large language models › Retrieval and knowledge · approach: Explanatory and multiple-choice QA benchmarks · 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 thinking-hierarchy algorithm instead of plurality votingPlurality voting · Mathquestions correct: 24 -> 29Improved
use thinking-hierarchy algorithm instead of plurality votingPlurality voting · Goquestions correct: 23 -> 28Improved
use thinking-hierarchy algorithm instead of plurality votingPlurality voting · General knowledgequestions correct: 35 -> 41Improved
use thinking-hierarchy algorithm instead of plurality votingPlurality voting · Chinese characterquestions correct: 34 -> 36Improved
use variant instead of default algorithm (ablation)Default algorithm · Chinese characterquestions correct: 36 -> 35Hurt
use variant instead of default algorithm (ablation)Default algorithm · Math, Go, General knowledgequestions correct: 29 -> 29No clear effect
rank by lack-of-fit index as reliabilityThinking hierarchy algorithm · all questionslack-of-fitImproved

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