Metraipolis › archive › dc_a747ffacb949

Cognitive Enhancement: Rethinking the Necessity of Role-Playing for Large Language Models — arXiv:2609.39853

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.39853
License (as archived)
CC0-1.0
Archived
2026-10-07T13:14:00.373Z
SHA-256 of the archived text
dd8cef1ddba2bcd3f5cb15963524d2cfed33a5ffe32caa47c33e5c65e811da9a
Stable URL of this page
https://metraipolis.com/documento/dc_a747ffacb949

How to cite

Cognitive Enhancement: Rethinking the Necessity of Role-Playing for Large Language Models — arXiv:2609.39853 — arXiv (en), https://arxiv.org/abs/2609.39853 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a747ffacb949 (Metraipolis archive dc_a747ffacb949, sha256 dd8cef1ddba2bcd3f5cb15963524d2cfed33a5ffe32caa47c33e5c65e811da9a)
BibTeX
@misc{dca747ffacb949,
  title = {Cognitive Enhancement: Rethinking the Necessity of Role-Playing for Large Language Models — arXiv:2609.39853},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.39853},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a747ffacb949; sha256 dd8cef1ddba2bcd3f5cb15963524d2cfed33a5ffe32caa47c33e5c65e811da9a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.39853. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Role-playing prompting has become a popular yet simple technique for improving LLM reasoning and output quality. However, whether it consistently boosts performance across diverse domains remains unclear, as systematic validation is lacking. To fill this gap, we run multi-model, cross-domain, and multilingual experiments on MMLU and MMLU-Redux. We find that gains from role-play prompting depend heavily on model capacity, knowledge domain, and prompt language. Drawing on metacognition theory, we propose the persona-related cognitive alignment hypothesis: role-play works only when the LLM correctly grasps the designated persona and its associated knowledge domain. We test this hypothesis through persona information richness ablation, layer-wise entropy divergence analysis, and latent thought-space deflection observation. To reduce persona cognitive bias and stabilize role-play performance, we propose \textbf{M}ixed-\textbf{L}anguage \textbf{C}oncatenate \textbf{P}rediction \textbf{(MLCP}), a simple, training-free, and efficient multilingual prompt concatenation strategy. It aggregates semantically equivalent role prompts to enrich complementary representational cues. Extensive experiments show that MLCP consistently outperforms vanilla role-play prompting across all tested LLMs.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2609.39853 — 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 2026-10-07T12:44:51.864Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).