Jasmine Xinze Li — accepted AI-conference papers

2026

EigenBench: A Comparative Behavioral Measure of Value Alignment

Jonathn Chang, Leonhard Piff, Suvadip Sana, Jasmine Xinze Li, Lionel Levine

ICLR 2026oral

Aligning AI with human values is a pressing unsolved problem. To address the lack of quantitative metrics for value alignment, we propose EigenBench: a black-box method for comparatively benchmarking language models’ values. Given an ensemble of models, a constitution describing a value system, and…

Cited by 0 Source ↗code ↗Scholar ↗

2024

ProgressGym: Alignment with a Millennium of Moral Progress

Tianyi Qiu, Yang Zhang, Xuchuan Huang, Jasmine Xinze Li, Jiaming Ji, Yaodong Yang

NeurIPS 2024spotlight

Frontier AI systems, including large language models (LLMs), hold increasing influence over the epistemology of human users. Such influence can reinforce prevailing societal values, potentially contributing to the lock-in of misguided moral beliefs and, consequently, the perpetuation of problematic…

Cited by 4 Source ↗PDF ↗code ↗Scholar ↗