AI Paper Atlas

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

Distributional Open-Ended Evaluation of LLM Cultural Value Alignment Based on Value Codebook

Jaehyeok Lee, Xiaoyuan Yi, Jing Yao, Hyunjin Hwang, Roy Ka-Wei Lee, Xing Xie, JinYeong Bak

ICML 2026 · Large language models › Language, safety and interpretability · approach: Controlled text generation · 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 value codebook (ablation)DOVE · Predictive validityPredictive validity: 5.49% -> 31.56%Improved
add codebook refinement (ablation)DOVE · Predictive validityPredictive validity: 8.98% -> 31.56%Improved
add UOT metric instead of cosine similarity (ablation)DOVE · Predictive validityPredictive validity: 13.16% -> 31.56%Improved
add redundancy reduction (ablation)DOVE · Predictive validityPredictive validity: 21.54% -> 31.56%Improved
use GPT-5.2 as value recognizer instead of GPT-5 nano (ablation)DOVE · Predictive validityPredictive validity: 28.11% -> 31.56%Improved
use GPT-5.2 as value recognizer instead of gpt-oss-120b (ablation)DOVE · Predictive validityPredictive validity: 28.62% -> 31.56%Improved
replace Mauve on document embeddings with Mauve on value code vectorsMauve · Predictive validityPredictive validity: -5.73% -> 29.78%Improved
use value expression embeddings rather than document embeddings for MauveMauve · Predictive validityPredictive validity: -5.73% -> 23.04%Improved
use UOT metric instead of Mauve on value code vectorsDOVE · Predictive validityPredictive validity: 29.78% -> 31.56%Improved
use DOVE open-ended evaluation instead of WVSevaluation method · Value primingValue priming Δg: 0.08% -> 5.60%Improved
use DOVE instead of NormAdevaluation method · Predictive validityPredictive validity: 0.90% -> 31.56%Improved
use DOVE instead of NaVAB for discriminant validityevaluation method · Discriminant validityDiscriminant validity δdis: -88.00% -> 0.89%Hurt

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