3 papers
cs.CL2025
CATCH: A Controllable Theme Detection Framework with Contextualized Clustering and Hierarchical Generation
Rui Ke, Jiahui Xu, Shenghao Yang +3
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 i…
cs.CL2025
Do We Really Need GNNs with Explicit Structural Modeling? MLPs Suffice for Language Model Representations
Li Zhou, Hao Jiang, Junjie Li +4
Explicit structural information has been proven to be encoded by Graph Neural Networks (GNNs), serving as auxiliary knowledge to enhance model capabilities and improve performance…
cs.CL2025
Know You First and Be You Better: Modeling Human-Like User Simulators via Implicit Profiles
Kuang Wang, Xianfei Li, Shenghao Yang +3
User simulators are crucial for replicating human interactions with dialogue systems, supporting both collaborative training and automatic evaluation, especially for large language…