AI Paper Atlas

Research map / Large language models / Agents, code and math

Do Large Language Models Reason About Uncertainty Like Humans? A Benchmark on Hurricane Forecast Visualization Comprehension

Le Liu, Yuhao Wang, Bohan Shen, Wei Zeng, Shizhou Zhang, Di Xu, Peng Wang

AAAI 2026 · Large language models › Agents, code and math · approach: Mathematical and structural reasoning benchmarks · 0 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 conversational context to GPT-4o (ablation)GPT-4o · Phase 1 central damage ratingdamage rating (beta): beta = -0.32Mixed
add conversational context to GPT-4o (ablation)GPT-4o · Phase 1 distance effect, cone-centerlineslope vs distance: -0.045 -> 0.021Mixed
add annotations of storm size and intensity to ensemble display (ablation)humans and GPT-4o · Phase 2 distance effectslope vs distance: human coef. 0.037; LLM w/ ctx 0.024; w/o ctx 0.012Improved
add annotations to representative-ensemble (ablation)GPT-4o · Phase 2 center ratingdamage rating (beta): humans -0.908; LLM w/o ctx +0.358; w/ ctx +0.938Mixed
add context to GPT-4o (ablation)GPT-4o · Phase 2 time x center effecttime effect alignment with humansImproved
add context to GPT-4o (ablation)GPT-4o · Phase 1 cone-only time effecttime x center beta: beta = -0.501Improved
use ensemble (implicit) instead of explicit cone display (ablation)GPT-4o without context · Phase 1 time x center48h vs 24h rating: ensemble beta = -1.300 vs cone-centerline +0.613Improved
add context to GPT-4o (ablation)GPT-4o · Phase 1 confidencemean confidence (1-7): 5 -> 6Mixed
add context to GPT-4o (ablation)GPT-4o · reasoning strategy distributionstrategy usageNo clear effect
add prompt clarification separating uncertainty from severity (ablation)GPT-4o · cone width misconceptionbiasImproved

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