CATCH: A Controllable Theme Detection Framework with Contextualized Clustering and Hierarchical Generation
This work addresses theme detection for dialogue systems, but it appears incremental as it builds on existing methods with improvements in handling sparse utterances and user preferences.
The paper tackled the problem of theme detection in user-centric dialogue systems, which requires identifying latent topics without predefined schemas while ensuring cross-dialogue consistency and personalization, and achieved effective results in theme clustering and topic generation quality on the DSTC-12 benchmark.
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.