Metraipolis › archive › dc_be58e8261bdc
MAVEN: A Macro-Societal Value Evaluation Framework of Multimodal Content with Compact Aligned Evaluators — arXiv:2608.18096
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.18096
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T13:53:38.670Z
- SHA-256 of the archived text
2504c924a8752b86fb9cf1c174c5cb5fe5c407c4ea3e00940acc45e814b0ef16- Stable URL of this page
https://metraipolis.com/documento/dc_be58e8261bdc
How to cite
MAVEN: A Macro-Societal Value Evaluation Framework of Multimodal Content with Compact Aligned Evaluators — arXiv:2608.18096 — arXiv (en), https://arxiv.org/abs/2608.18096 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_be58e8261bdc (Metraipolis archive dc_be58e8261bdc, sha256 2504c924a8752b86fb9cf1c174c5cb5fe5c407c4ea3e00940acc45e814b0ef16)
BibTeX
@misc{dcbe58e8261bdc,
title = {MAVEN: A Macro-Societal Value Evaluation Framework of Multimodal Content with Compact Aligned Evaluators — arXiv:2608.18096},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.18096},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_be58e8261bdc; sha256 2504c924a8752b86fb9cf1c174c5cb5fe5c407c4ea3e00940acc45e814b0ef16},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.18096. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Assessing whether multimodal content aligns with macro-societal values, such as peace, justice, and freedom, has become an increasingly urgent challenge. Existing frameworks are largely confined to safety-oriented taxonomies, text-only psychometric probes, or single-label classification. Therefore, we propose MAVEN, a hierarchical framework for macro-societal value evaluation of multimodal content, grounded in international human-rights instruments and cultural value theory. MAVEN organizes values into 6 primary dimensions and 72 secondary indicators, supporting multi-level quantitative scoring. Building on MAVEN, we construct a human-verified multimodal benchmark and a soft-match metric to evaluate VLMs' assessments across value dimensions. For evaluator optimization, we propose a span-adaptive variant of multi-level preference optimization for evaluator distillation, together with a training-free multi-role consensus strategy at inference time. We evaluate existing open- and closed-source VLMs on our benchmark, revealing shared tendencies and clear differences in macro-societal value judgments. Experiments show that our compact 2B evaluator matches its 8B counterpart in the same family and approaches frontier closed-source VLMs, offering a practical path toward scalable macro-societal value evaluation. Our SA-MDPO implementation and MacroValue-Bench are available at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-20 in cs.LG). Categorie arXiv: Computation and Language (cs.CL) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2608.18096 — 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 2026-10-18T13:50:58.972Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-20?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).