Metraipolis › archive › dc_904dc95b030d

ODRA: Synthesizing Cognitive Behavioral Therapy Sessions with Structured Chain-Of-Thought and Dynamic Patient Resistance — arXiv:2608.04524

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.04524
License (as archived): CC0-1.0
Archived: 2026-10-31T11:24:41.035Z
SHA-256 of the archived text: 9a79cd9aaea469e79f619122a6f7716e64596e1492663a6ac6b43bdc777fa7ec
Stable URL of this page: https://metraipolis.com/documento/dc_904dc95b030d

How to cite

ODRA: Synthesizing Cognitive Behavioral Therapy Sessions with Structured Chain-Of-Thought and Dynamic Patient Resistance — arXiv:2608.04524 — arXiv (en), https://arxiv.org/abs/2608.04524 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_904dc95b030d (Metraipolis archive dc_904dc95b030d, sha256 9a79cd9aaea469e79f619122a6f7716e64596e1492663a6ac6b43bdc777fa7ec)

BibTeX

@misc{dc904dc95b030d,
  title = {ODRA: Synthesizing Cognitive Behavioral Therapy Sessions with Structured Chain-Of-Thought and Dynamic Patient Resistance — arXiv:2608.04524},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.04524},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_904dc95b030d; sha256 9a79cd9aaea469e79f619122a6f7716e64596e1492663a6ac6b43bdc777fa7ec},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.04524. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Synthetic generation of Cognitive Behavioral Therapy (CBT) sessions is challenged by two competing demands: adhering to strict therapeutic structure while modeling the resistant, unpredictable behavior of real patients. Existing script-based methods fail to capture dynamic therapeutic interactions, while multi-agent approaches struggle to adhere to CBT's sequential structure; both suffer from sycophancy, producing overly compliant patients that misrepresent real clinical settings. In this work we introduce ODRA, a novel framework for synthesizing therapy dialogues through a Chain-of-Thought (CoT) strategy grounded in foundational CBT guidelines (Beck, 2020). ODRA further incorporates a resistance orchestrator to solve patient sycophancy, which employs steering techniques to elicit behaviors aligned with their resistance level. Automated and expert evaluations show that ODRA significantly outperforms existing methods across therapeutic skills, CBT alignment, and patient behavioral fidelity, with licensed psychologists preferring ODRA sessions across 12 of 13 clinical metrics. Furthermore, models fine-tuned on our dataset demonstrate superior therapeutic performance against both cooperative and resistant patients, validating that explicit resistance modeling in synthetic training data directly translates to downstream clinical robustness.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-06 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.04524 — 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 2026-10-31T11:13:23.173Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-06?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).