Behavior Tokens Speak Louder: Disentangled Explainable Recommendation with Behavior Vocabulary
Xinshun Feng, Mingzhe Liu, Yi Qiao, Tongyu Zhu, Leilei Sun, Shuai Wang

TL;DR
BEAT introduces a behavior vocabulary that tokenizes user and item behaviors into interpretable sequences, enhancing explainable recommendation systems by improving zero-shot performance and explanation coherence.
Contribution
The paper proposes a novel behavior tokenization framework using vector-quantized autoencoding and semantic supervision, enabling better interpretability and transferability in explainable recommendation models.
Findings
BEAT improves zero-shot recommendation accuracy.
Behavior tokens capture fine-grained semantics.
The framework generates coherent, informative explanations.
Abstract
Recent advances in explainable recommendations have explored the integration of language models to analyze natural language rationales for user-item interactions. Despite their potential, existing methods often rely on ID-based representations that obscure semantic meaning and impose structural constraints on language models, thereby limiting their applicability in open-ended scenarios. These challenges are intensified by the complex nature of real-world interactions, where diverse user intents are entangled and collaborative signals rarely align with linguistic semantics. To overcome these limitations, we propose BEAT, a unified and transferable framework that tokenizes user and item behaviors into discrete, interpretable sequences. We construct a behavior vocabulary via a vector-quantized autoencoding process that disentangles macro-level interests and micro-level intentions from…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
Taxonomy
TopicsExplainable Artificial Intelligence (XAI) · Multimodal Machine Learning Applications · Topic Modeling
