@inproceedings{wang-etal-2026-humanllm,
    title = "{H}uman{LLM}: Benchmarking and Improving {LLM} Anthropomorphism via Human Cognitive Patterns",
    author = "Wang, Xintao  and
      Yang, Jian  and
      Li, Weiyuan  and
      Xie, Rui  and
      Huang, Jen-tse  and
      Gao, Jun  and
      Huang, Shuai  and
      Kang, Yueping  and
      Guo, Yuanli  and
      Feng, Hongwei  and
      Xiao, Yanghua",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.1783/",
    pages = "38486--38517",
    ISBN = "979-8-89176-390-6",
    abstract = "Large Language Models (LLMs) have demonstrated remarkable capabilities in reasoning and generation, serving as the foundation for advanced persona simulation and Role-Playing Language Agents (RPLAs). However, achieving authentic alignment with human cognitive and behavioral patterns remains a critical challenge for these agents. We present HumanLLM, a framework treating psychological patterns as interacting causal forces.We construct 244 patterns from $\sim$12,000 academic papers and synthesize 11,359 scenarios where 2-5 patterns reinforce, conflict, or modulate each other, with multi-turn conversations expressing inner thoughts, actions, and dialogue.Our dual-level checklists evaluate both individual pattern fidelity and emergent multi-pattern dynamics, achieving strong human alignment ($r=0.90$) while revealing that holistic metrics conflate simulation accuracy with social desirability.HumanLLM-8B outperforms Qwen3-32B on multi-pattern dynamics despite 4$\times$ fewer parameters, demonstrating that authentic anthropomorphism requires cognitive modeling{---}simulating not just what humans do, but the psychological processes generating those behaviors.Our dataset, code, and model are available at:https://github.com/YJGoodbye2024/HumanLLM"
}