IROTE: Human-like Traits Elicitation of Large Language Model via In-Context Self-Reflective Optimization
Yuzhuo Bai, Shitong Duan, Muhua Huang, Jing Yao, Zhenghao Liu, Peng Zhang, Tun Lu, Xiaoyuan Yi
Abstract
Trained on various human-authored corpora, Large Language Models (LLMs) have demonstrated a certain capability of reflecting specific human-like traits (e.g., personality or values) by prompting, benefiting applications like personalized LLMs and social simulations. However, existing methods suffer from the superficial elicitation problem: LLMs can only be steered to mimic shallow and unstable stylistic patterns, failing to embody the desired traits precisely and consistently across diverse tasks like humans. To address this challenge, we propose IROTE, a novel in-context method for stable and transferable trait elicitation. Drawing on psychological theories suggesting that traits are formed through identity-related reflection, our method automatically generates and optimizes a textual self-reflection within prompts, which comprises self-perceived experience, to stimulate LLMs
BibTeX
@inproceedings{aaai2026_irotehumanliketr,
title = {IROTE: Human-like Traits Elicitation of Large Language Model via In-Context Self-Reflective Optimization},
author = {Yuzhuo Bai and Shitong Duan and Muhua Huang and Jing Yao and Zhenghao Liu and Peng Zhang and Tun Lu and Xiaoyuan Yi and Maosong Sun and Xing Xie},
booktitle = {AAAI 2026},
year = {2026}
}