Metraipolis › archive › dc_e43cff89d133
Cross-Model Humor Preference Modeling with Cards Against Humanity — arXiv:2608.07481
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.07481
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T08:59:18.534Z
- SHA-256 of the archived text
a1c1b1562050f1023fcf455615931a2e8bac35f3f47a38334b771aac7779d50d- Stable URL of this page
https://metraipolis.com/documento/dc_e43cff89d133
How to cite
Cross-Model Humor Preference Modeling with Cards Against Humanity — arXiv:2608.07481 — arXiv (en), https://arxiv.org/abs/2608.07481 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e43cff89d133 (Metraipolis archive dc_e43cff89d133, sha256 a1c1b1562050f1023fcf455615931a2e8bac35f3f47a38334b771aac7779d50d)
BibTeX
@misc{dce43cff89d133,
title = {Cross-Model Humor Preference Modeling with Cards Against Humanity — arXiv:2608.07481},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.07481},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e43cff89d133; sha256 a1c1b1562050f1023fcf455615931a2e8bac35f3f47a38334b771aac7779d50d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.07481. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
This paper investigates whether one large language model can approximate the humor preferences of another in a controlled Cards Against Humanity-style task. Two models - GPT-4o as Czar and Claude Opus-4.5 as Player - are evaluated on a binary humor-selection task constructed so that success cannot follow from self-preference. A reflected-cell stability procedure isolates 244 hands on which the two models hold deterministic but opposite preferences, partitioned into a 97-hand context pool and a 147-hand held-out test pool. The Player is then evaluated across five graded conditions: default self-preference, generic Czar-modeling instruction, model-identified Czar, prior Czar selections, and prior Czar selections with rationales. This gradient is designed to separate two sources of improvement: framing effects, in which the Player is told to attend to a Czar without seeing any of the Czar's behavior, and direct behavioral evidence, in which the Player is shown the Czar's prior choices. Player accuracy increased from 0.7% in Condition 1 to 19.0% and 25.9% in the framing-only conditions, and then rose to 72.8% and 82.3% once behavioral evidence and rationales were provided. An omnibus Cochran's Q test and pairwise McNemar tests confirmed that each step in the gradient produced a significant improvement. The results indicate that role instruction and model identity yield only modest gains, while behavioral evidence - especially when accompanied by rationales - supports substantial cross-model preference modeling. The findings are interpreted as theory-of-mind-like behavior in an operational rather than representational sense: the Player shifts away from self-preference toward another agent's demonstrated preferences, without any claim about an underlying representation of mental states. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-11 in cs.HC). Categorie arXiv: Human-Computer Interaction (cs.HC) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.07481 — 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 2026-10-19T08:54:55.967Z dalla pagina https://arxiv.org/catchup/cs.HC/2026-08-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).