Metraipolis › archive › dc_b2d300414afe

ExpertIVS: Sociological Expert Driven Individual Value Simulation in Large Language Models — arXiv:2608.20355

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.20355
License (as archived)
CC0-1.0
Archived
2026-10-18T10:18:07.540Z
SHA-256 of the archived text
ecac2c1d019e7d80e3cd607d330749493ce4f6799751dce345a7116a92c79b78
Stable URL of this page
https://metraipolis.com/documento/dc_b2d300414afe

How to cite

ExpertIVS: Sociological Expert Driven Individual Value Simulation in Large Language Models — arXiv:2608.20355 — arXiv (en), https://arxiv.org/abs/2608.20355 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b2d300414afe (Metraipolis archive dc_b2d300414afe, sha256 ecac2c1d019e7d80e3cd607d330749493ce4f6799751dce345a7116a92c79b78)
BibTeX
@misc{dcb2d300414afe,
  title = {ExpertIVS: Sociological Expert Driven Individual Value Simulation in Large Language Models — arXiv:2608.20355},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.20355},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b2d300414afe; sha256 ecac2c1d019e7d80e3cd607d330749493ce4f6799751dce345a7116a92c79b78},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.20355. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large Language Model (LLM) agents have demonstrated considerable potential for social simulation, yet struggle to accurately model individual value systems. Most existing methods mechanically stitch survey responses into prompts, which suffer from semantic fragmentation, failing to capture the internal coherence of human value systems. The value systems of LLMs are typically assessed using static multiple-choice questions, which fail to evaluate the value orientation in real-world dialogue interactions. To address these issues, we propose ExpertIVS, a framework employing 14 Sociological Expert Agents to interpret World Values Survey (WVS) responses through structured professional perspectives, rather than direct responses concatenation. These expert agents perform deep semantic reconstruction to generate robust and internally consistent individual profiles. To evaluate the consistency between LLMs and individual value systems during dynamic interactions, we further introduce a multi-agent debate mechanism. Extensive experiments across 480 individuals from 12 countries demonstrate that ExpertIVS achieves 90.78% value restoration fidelity and significantly outperforms baselines in value generalization (+5.3%). Moreover, ExpertIVS exhibits strong personality discriminability and behavioral consistency, enabling a shift from mere response concatenation to genuine sociological role-playing.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-24 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.20355 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-18T10:17:37.548Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).