15 papers
The Road to Artificial SuperIntelligence: A Comprehensive Survey of Superalignment
HyunJin Kim, DongHyun Ryu, Xiaoyuan Yi +6
The emergence of large language models (LLMs) has sparked discussion on Artificial Superintelligence (ASI), a hypothetical AI system that surpasses human intelligence. Although ASI…
Can Persona-Prompted LLMs Emulate Subgroup Values? An Empirical Analysis of Generalisability and Fairness in Cultural Alignment
Bryan Chen Zhengyu Tan, Zhengyuan Liu, Xiaoyuan Yi +4
Despite their global prevalence, many Large Language Models (LLMs) are aligned to a monolithic, often Western-centric set of values. This paper investigates the more challenging ta…
Human Values Matter: Investigating How Misalignment Shapes Collective Behaviors in LLM Agent Communities
Xiangxu Zhang, Jiamin Wang, Qinlin Zhao +6
As LLMs become increasingly integrated into human society, evaluating their orientations on human values from social science has drawn growing attention. Nevertheless, it is still…
CAReDiO: Cultural Alignment via Representativeness and Distinctiveness Guided Data Optimization
Jing Yao, Xiaoyuan Yi, Jindong Wang +2
As Large Language Models (LLMs) are deployed across diverse regions, aligning them with pluralistic cultures is crucial for improving user engagement and mitigating cultural confli…
AdAEM: An Adaptively and Automated Extensible Measurement of LLMs' Value Difference
Jing Yao, Shitong Duan, Xiaoyuan Yi +6
Assessing Large Language Models'(LLMs) underlying value differences enables comprehensive comparison of their misalignment, cultural adaptability, and biases. Nevertheless, current…
Research Superalignment Should Advance Now with Alternating Competence and Conformity Optimization
HyunJin Kim, Xiaoyuan Yi, Jing Yao +4
The recent leap in AI capabilities, driven by big generative models, has sparked the possibility of achieving Artificial General Intelligence (AGI) and further triggered discussion…