Multicultural multi-agent LLM systems exhibit substantially lower value diversity than human societies on the World Values Survey, with diversity uncorrelated to per-agent alignment and further reduced by agent interactions.
C ulture B ank: An Online Community-Driven Knowledge Base Towards Culturally Aware Language Technologies
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 6verdicts
UNVERDICTED 6roles
background 1polarities
background 1representative citing papers
KG-FairDiff is an inference-time framework that uses a knowledge graph to guide prompt refinement and reduce gender, race, age, and intersectional biases in text-to-image generation while preserving semantics.
JuICE is a new multilingual benchmark dataset showing top LLM judges reach only F1 0.52 on span-level cultural error detection and miss errors locals readily spot.
Researchers created a stigma-aware WhatsApp chatbot for menstrual health education in Pakistan through co-design workshops and a two-week deployment, yielding insights on its use for challenging taboos alongside tensions around trust and cultural explanations.
A multilingual self-consistency plus self-critique method raises cultural alignment scores on English queries by 5.03% on the BLEnD benchmark using only self-generated data.
Jupiter-N is a post-trained version of Nemotron 3 Super that reports gains on Welsh benchmarks, terminal agent tasks, and instruction following while retaining base capabilities, released openly as a template for sovereign cultural AI adaptation.
citing papers explorer
-
Beyond Alignment: Value Diversity as a Collective Property in Multicultural Agent Systems
Multicultural multi-agent LLM systems exhibit substantially lower value diversity than human societies on the World Values Survey, with diversity uncorrelated to per-agent alignment and further reduced by agent interactions.
-
JuICE: A Benchmark for Evaluating LLM-Judge in Identifying Cultural Errors
JuICE is a new multilingual benchmark dataset showing top LLM judges reach only F1 0.52 on span-level cultural error detection and miss errors locals readily spot.
-
Cross-Lingual Consensus: Aligning Multilingual Cultural Knowledge via Multilingual Self-Consistency
A multilingual self-consistency plus self-critique method raises cultural alignment scores on English queries by 5.03% on the BLEnD benchmark using only self-generated data.
-
Jupiter-N Technical Report
Jupiter-N is a post-trained version of Nemotron 3 Super that reports gains on Welsh benchmarks, terminal agent tasks, and instruction following while retaining base capabilities, released openly as a template for sovereign cultural AI adaptation.