Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

CATCH: A Controllable Theme Detection Framework with Contextualized Clustering and Hierarchical Generation

About

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.

Rui Ke, Jiahui Xu, Shenghao Yang, Kuang Wang, Feng Jiang, Haizhou Li• 2025

Related benchmarks

TaskDatasetResultRank
Theme DetectionDSTC Travel domain 12 (test)
Semantic Relevance (SR)86.2
6
Conversation-level Topic Discovery and LabelingDSTC-12 Travel domain (blind test)
Accuracy0.358
6
Theme DistributionFinance Out-of-domain
Accuracy55.8
4
Theme DistributionInsurance Out-of-domain
Acc54.5
4
Theme DistributionBANKING
Acc0.567
4
Theme Label QualityFinance Out-of-domain
ROUGE-142.4
4
Theme Label QualityInsurance Out-of-domain
ROUGE-141.8
4
Theme Label QualityBANKING
ROUGE-135.3
4
Showing 8 of 8 rows

Other info

Follow for update