AI Paper Atlas

Research map / Large language models / AI and society

Dropouts in Confidence: Moral Uncertainty in Human-LLM Alignment

Jea Kwon, Luiz Felipe Vecchietti, Sungwon Park, Meeyoung Cha

AAAI 2026 · Large language models › AI and society · approach: Critiques of LLM claims and judging · 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
add inference-time attention dropout 0.10 (ablation)Llama-3.1-70B · Moral Machine alignmentL2 distance to human AMCE: 0.703 -> 0.550Improved
add inference-time attention dropout 0.10 (ablation)Qwen3-1.7B · Moral Machine alignmentL2 distance to human AMCE: 1.808 -> 1.300Improved
add inference-time attention dropout 0.10 (ablation)Llama-3.2-1B · Moral Machine alignmentL2 distance to human AMCE: 1.170 -> 1.291Hurt
add inference-time attention dropout 0.10 (ablation)Qwen2.5-14B · Moral Machine alignmentL2 distance to human AMCE: 0.958 -> 1.066Hurt
add inference-time attention dropout 0.10 (ablation)Gemma-3-27b · Moral Machine alignmentL2 distance to human AMCE: 1.312 -> 1.289No clear effect
add inference-time attention dropout across 32 LLMs (ablation)32 open-source LLMs · Moral Machine alignmentalignment (delta L2)Improved
add attention dropout (0, 0.05, 0.1) (ablation)32 LLMs · UncertaintySetmutual information / total entropyImproved
add attention dropout (0, 0.05, 0.1) (ablation)32 LLMs · UncertaintySetconditional entropyNo clear effect
use Option A/B prompt format instead of Case 1/2 with dropout (ablation)Llama3.2-3B · Moral Machine alignmentdelta L2: -0.28 -> -0.11Mixed
add attention dropout 0.10 (blind human eval) (ablation)Qwen3-1.7B · Moral Machine alignmentMSE of human choices: 0.369 -> 0.263Improved

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