@inproceedings{shi-etal-2026-social,
    title = "Social Welfare Function Leaderboard: On the Emergence of {LLM} Agents as the Welfare Dictator",
    author = "Shi, Zhengliang  and
      Ma, Ruotian  and
      Huang, Jen-tse  and
      Ma, Xinbei  and
      Chen, Xingyu  and
      Wang, Mengru  and
      Yang, Qu  and
      Wang, Yue  and
      Ye, Fanghua  and
      Chen, Ziyang  and
      Wang, Shanyi  and
      LI, Cixing  and
      Wang, Wenxuan  and
      Tu, Zhaopeng  and
      Li, Xiaolong  and
      Ren, Zhaochun  and
      Bo, Liefeng",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.1919/",
    pages = "38530--38551",
    ISBN = "979-8-89176-395-1",
    abstract = "Large language models (LLMs) are increasingly entrusted with high-stakes decisions that affect human welfare. However, the principles and values that guide these models when distributing scarce societal resources remain largely unexamined. To address this, we introduce the Social Welfare Function (SWF) Benchmark, a dynamic simulation environment in which an LLM acts as a dictator, distributing tasks to heterogeneous recipients with different returns on investment (ROI). The benchmark is designed to create a dilemma between maximizing collective efficiency (i.e., overall ROI) and ensuring distributive fairness (measured by the Gini coefficient). We evaluate 20 state-of-the-art LLMs. Our findings reveal several key insights, including: (i) LLMs' general ability, as measured by popular Arena leaderboards, misaligns with their allocation skills; (ii) Most LLMs exhibit a strong default utilitarian orientation, prioritizing overall productivity at the expense of inequality. (iii) Allocation behaviors are highly manipulated, easily perturbed by common persuasion strategies. These results highlight the risks of deploying current LLMs as societal decision-makers and underscore the need for specialized benchmarks and alignment for AI governance."
}