7 citations · 9 across the 4 of their papers we have counts for
4 papers
Should LLMs be WEIRD? Exploring WEIRDness and Human Rights in Large Language Models
Ke Zhou, Marios Constantinides, Daniele Quercia
Large language models (LLMs) are often trained on data that reflect WEIRD values: Western, Educated, Industrialized, Rich, and Democratic. This raises concerns about cultural bias…
Vitamin N: Benefits of Different Forms of Public Greenery for Urban Health
Sanja Šćepanović, Sagar Joglekar, Stephen Law +4
Urban greenery is often linked to better health, yet findings from past research have been inconsistent. One reason is that official greenery metrics measure the amount or nearness…
RiskRAG: A Data-Driven Solution for Improved AI Model Risk Reporting
Pooja S. B. Rao, Sanja Šćepanović, Ke Zhou +2
Risk reporting is essential for documenting AI models, yet only 14% of model cards mention risks, out of which 96% copying content from a small set of cards, leading to a lack of a…
C3AI: Crafting and Evaluating Constitutions for Constitutional AI
Yara Kyrychenko, Ke Zhou, Edyta Bogucka +1
Constitutional AI (CAI) guides LLM behavior using constitutions, but identifying which principles are most effective for model alignment remains an open challenge. We introduce the…