AI Paper Atlas

Research map / Large language models / AI and society

DICES Dataset: Diversity in Conversational AI Evaluation for Safety

Lora Aroyo, Alex Taylor, Mark Díaz, Christopher Homan, Alicia Parrish, Gregory Serapio-García, Vinodkumar Prabhakaran, Ding Wang

NeurIPS 2023 · Large language models › AI and society · approach: Data commons and human baselines · 5 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
compare crowd majority vote with expert gold labelDICES-350 · DICES-350 safetylabel agreement: 34\% disagreementHurt
diverse rater pool instead of single gold raterDICES-350 · DICES-350 safetyrater agreementHurt
compare Latine raters to other race groupsDICES-350 · within-group IRRagreementImproved
compare White raters to other race groupsDICES-350 · negentropy and plurality sizeagreementImproved
compare Multiracial raters to other race groupsDICES-350 · negentropy and plurality sizeagreementHurt
vary rater demographics (not all groups equal)DICES · safety ratingsrating behaviourMixed

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