AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

Robust Human-AI Complementarity under Uncertainty

Yewon Byun, Bryan Wilder

ICML 2026 · Learning theory and algorithms › Prediction and decision losses · approach: Data attribution and recourse · 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
prompt LLM for contrarian reasoning (ablation)GPT-5 forecasts · ForecastBencherror correlation with humans: 0.963 -> 0.498Improved
prompt LLM for contrarian reasoning (ablation)GPT-5 forecasts · TESS studieserror correlation with humans: 0.216 -> -0.338Improved
prompt LLM with direct error correction (ablation)GPT-5 forecasts · ForecastBencherror correlation with humans: 0.963 -> 0.995Hurt
prompt LLM with self-divergent reasoning (ablation)GPT-5 forecasts · ForecastBencherror correlation with humans: 0.963 -> 0.966No clear effect
prompt LLM with human-divergent reasoning (ablation)GPT-5 forecasts · ForecastBencherror correlation with humans: 0.963 -> 0.985No clear effect
restrict LLM context (different information set) (ablation)GPT-5 forecasts · ForecastBencherror correlation with humans: 0.963 -> 0.967No clear effect
combine human and LLM via robust rule instead of calibrated human onlyRobust combination · ForecastBenchMSE: 0.154 -> 0.154No clear effect
combine human and LLM via robust rule with contrarian promptRobust combination · TESS studiesMSE: 0.00524 -> 0.00490Improved
combine human and LLM via robust rule with contrarian promptRobust combination · ForecastBenchMSE: 0.154 -> 0.153Improved
increase human-AI error correlation in simulation (ablation)Robust estimator · synthetic Gaussian MSEMSE gainHurt
increase expert noise under positive error correlation (rho=0.75) (ablation)Robust estimator · synthetic MSEMSE gainImproved

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