Yi-Long Lu — accepted AI-conference papers

2026

From Five Dimensions to Many: Large Language Models as Precise and Interpretable Psychological Profilers

Yi-Fei Liu, Yi-Long Lu, Di He, Hang Zhang

ICLR 2026poster

Psychological constructs within individuals are widely believed to be interconnected. We investigated whether and how Large Language Models (LLMs) can model the correlational structure of human psychological traits from minimal quantitative inputs. We prompted various LLMs with Big Five Personality…

Cited by 0 Source ↗code ↗Scholar ↗

2026

Mind the Gap: The Divergence Between Human and LLM-Generated Tasks

Yi-Long Lu, Jiajun Song, Chunhui Zhang, Wei Wang

AAAI 2026technical

Humans constantly generate a diverse range of tasks guided by internal motivations. While generative agents powered by large language models (LLMs) aim to simulate this complex behavior, it remains uncertain whether they operate on similar cognitive principles. To address this, we conducted a task-g

Cited by 0 Source ↗PDF ↗Scholar ↗