CCDWIKI: Decoupling Case Formulation from Response Generation in Longitudinal CBT Dialogue

Computer Science > Computation and Language arXiv:2611.05383 (cs) [Submitted on 31 Jul 2026] Title:CCDWIKI: Decoupling Case Formulation from Response Generation in Longitudinal CBT Dialogue Authors:Mingwen Zhang, Ruiyang Song, Qinying Wang, Yuchen Wang, Changsheng Ma, Minqiang Yang.

计算机科学 > 计算与语言 arXiv:2611.05383 (cs) [提交于 2026 年 7 月 31 日] 标题：CCDWIKI：在纵向 CBT 对话中将案例构思与响应生成解耦。作者：Mingwen Zhang, Ruiyang Song, Qinying Wang, Yuchen Wang, Changsheng Ma, Minqiang Yang。

Abstract: Cognitive Behavioral Therapy (CBT) demands more than empathic validation, requiring instead a structured formulation of the interplay among situations, automatic thoughts, emotions, and behaviors. Therapists formalize this interplay through a Cognitive Conceptualization Diagram, where maintaining longitudinal coherence necessitates continuous evidential adjudication to separate tentative hypotheses from established findings.

摘要：认知行为疗法（CBT）不仅仅需要共情验证，还需要对情境、自动思维、情绪和行为之间的相互作用进行结构化的构思。治疗师通过认知概念化图表将这种相互作用形式化，其中保持纵向连贯性需要持续的证据裁决，以将初步假设与既定发现区分开来。

Current dialogue systems track conversational history via retrieval or static profiles but lack the representational capacity to encode epistemic status. Consequently, provisional interpretations are often prematurely reified as established facts, inadvertently biasing downstream interventions.

当前的对话系统通过检索或静态配置文件来跟踪对话历史，但缺乏编码认知状态的表征能力。因此，临时解释往往过早地被具体化为既定事实，从而无意中偏向了后续的干预措施。

Addressing this limitation, CCDWiki is introduced as a plug-and-play advisor conceptualizing longitudinal therapy as evidence-grounded hypothesis adjudication. The approach encodes each clinical hypothesis as a mutable entry bound to corroborating and contradicting evidence.

为了解决这一局限性，CCDWiki 被引入作为一个即插即用的顾问，将纵向治疗概念化为基于证据的假设裁决。该方法将每个临床假设编码为一个可变条目，并绑定到支持和反驳的证据上。

Across sessions, accumulating data strengthens supported entries, preserves provisional ones, and retracts contradicted assumptions. The resulting formulation distills into concise guidance for unmodified therapeutic language models. Experiments demonstrate substantial improvements in both conceptualization and intervention quality without requiring backbone retraining.

在多次会话中，积累的数据会加强受支持的条目，保留临时的条目，并撤回被反驳的假设。由此产生的构思被提炼为针对未经修改的治疗语言模型的简洁指导。实验表明，在无需重新训练骨干模型的情况下，概念化和干预质量均有显著提高。