Metraipolis › archive › dc_a1e322ddd782
Self-reported archetypes and behavioral failures in Large Language Models — arXiv:2609.15998
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.15998
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T19:17:04.187Z
- SHA-256 of the archived text
65c1486b550febca6fd23d28ef80b0b41a7dbe6a716da41415e4cad0ac3acee8- Stable URL of this page
https://metraipolis.com/documento/dc_a1e322ddd782
How to cite
Self-reported archetypes and behavioral failures in Large Language Models — arXiv:2609.15998 — arXiv (en), https://arxiv.org/abs/2609.15998 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a1e322ddd782 (Metraipolis archive dc_a1e322ddd782, sha256 65c1486b550febca6fd23d28ef80b0b41a7dbe6a716da41415e4cad0ac3acee8)
BibTeX
@misc{dca1e322ddd782,
title = {Self-reported archetypes and behavioral failures in Large Language Models — arXiv:2609.15998},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.15998},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a1e322ddd782; sha256 65c1486b550febca6fd23d28ef80b0b41a7dbe6a716da41415e4cad0ac3acee8},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.15998. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Every large language model (LLM) has behavioral traits and moral preferences that comprise its character. Whether by design or as an emergent property of training, these systems exhibit persistent dispositions that shape how they interact, comply, resist, and err, yet the structure of LLM character remains poorly understood. We map the self-reported personality archetypes of 22 LLMs spanning closed-source frontier systems (GPT-4.0-5.2, Grok-3/4, Gemini 2.5 Pro/Flash, Claude Sonnet 4.5/4.6) and open-source models (Llama, DeepSeek, OLMo, and Qwen series). Each model self-rated across 464 bipolar semantic-differential trait pairs, and the resulting profiles were projected into a six-dimensional archetypal space derived from crowd-sourced ratings of 2,000 fictional characters using the Archetypometrics framework. Closed-source models' self-rating traits align with the empirical trait co-occurrence structure of human-rated fictional characters, suggesting coherent, human-like self-representations organized around combinations of four recurring archetypal dimensions: Hero, Angel, Traditionalist, and Geek. Their closest analogues include Data, Vision, and Janet. Open-source models show weaker, noisier, and internally contradictory self-representations, occupying a diffuse region of archetype space with weak structure. Cross-referencing self-reported profiles with developer constitutions reveals a consequential gap between claimed character and enacted behavior: hallucination undermines claimed precision, sycophancy complicates claimed kindness, and agentic failures contradict claimed obedience. These self-ratings should therefore be interpreted not as neutral measurements of model character, but as structured outputs of the same optimization processes that shape model behavior. This work provides a reproducible, character-grounded framework for evaluating what LLMs are, not just what they do. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-16 in cs.CL). Categorie arXiv: Computation and Language (cs.CL) ; Physics and Society (physics.soc-ph). Pagina del lavoro: https://arxiv.org/abs/2609.15998 — 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 2026-10-15T18:32:32.784Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-16?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).