CATCH：一个具有上下文聚类和层次生成的可控主题检测框架
CATCH: A Controllable Theme Detection Framework with Contextualized Clustering and Hierarchical Generation
AI总结：
CATCH提出了一种可控主题检测框架，通过上下文聚类和层次生成机制，解决稀疏语句和用户偏好识别的问题，提升对话系统中主题检测的准确性和一致性。
摘要：
主题检测是用户导向对话系统中的基本任务，旨在在不依赖预定义模式的情况下识别每条语句的潜在主题。与意图诱导不同，主题检测需要跨对话的一致性和与个性化用户偏好的一致性，这带来了重大挑战。现有方法往往难以对稀疏、简短的语句进行准确的主题表示，并且无法在对话中捕捉到用户层面的主题偏好。为了解决这些挑战，我们提出了CATCH（具有上下文聚类和层次生成的可控主题检测），一个统一的框架，集成了三个核心组件：（1）上下文感知的主题表示，通过周围的主题段丰富语句层面的语义；（2）偏好引导的主题聚类，联合建模语义接近性和个性化反馈，以在对话中对齐主题；（3）一个层次主题生成机制，设计用于抑制噪声并生成稳健、连贯的主题标签。在多领域客户对话基准（DSTC-12）上的实验表明，CATCH在8B LLM中在主题聚类和主题生成质量上都表现出有效性。
英文摘要：
Theme detection is a fundamental task in user-centric dialogue systems, aiming to identify the latent topic of each utterance without relying on predefined schemas. Unlike intent induction, which operates within fixed label spaces, theme detection requires cross-dialogue consistency and alignment with personalized user preferences, posing significant challenges. Existing methods often struggle with sparse, short utterances for accurate topic representation and fail to capture user-level thematic preferences across dialogues. To address these challenges, we propose CATCH (Controllable Theme Detection with Contextualized Clustering and Hierarchical Generation), a unified framework that integrates three core components: (1) context-aware topic representation, which enriches utterance-level semantics using surrounding topic segments; (2) preference-guided topic clustering, which jointly models semantic proximity and personalized feedback to align themes across dialogue; and (3) a hierarchical theme generation mechanism designed to suppress noise and produce robust, coherent topic labels. Experiments on a multi-domain customer dialogue benchmark (DSTC-12) demonstrate the effectiveness of CATCH with 8B LLM in both theme clustering and topic generation quality.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
