G-UBS: Towards Robust Understanding of Implicit Feedback via Group-Aware User Behavior Simulation

TL;DR

The paper tackles the problem of noisy implicit feedback in video recommendation by proposing G-UBS, a group-aware user behavior simulation framework with two collaborating agents: UGM, which derives robust group profiles through summarize-cluster-reflect, and UFM, which uses group guidance in RL to better interpret implicit feedback. A novel IF-VR multimodal dataset is introduced to evaluate implicit feedback understanding in realistic scenarios, including sequential recommendations and click simulations. Empirical results show that G-UBS outperforms strong LLMs, MLLMs, and traditional simulators on IF-VR and public datasets, notably improving play rates and reasoning accuracy. The work demonstrates that integrating group-level guidance with individual user modeling yields more robust interpretation of implicit signals and more effective downstream recommendations, with practical implications for scalable, multimodal recommender systems.

Abstract

User feedback is critical for refining recommendation systems, yet explicit feedback (e.g., likes or dislikes) remains scarce in practice. As a more feasible alternative, inferring user preferences from massive implicit feedback has shown great potential (e.g., a user quickly skipping a recommended video usually indicates disinterest). Unfortunately, implicit feedback is often noisy: a user might skip a video due to accidental clicks or other reasons, rather than disliking it. Such noise can easily misjudge user interests, thereby undermining recommendation performance. To address this issue, we propose a novel Group-aware User Behavior Simulation (G-UBS) paradigm, which leverages contextual guidance from relevant user groups, enabling robust and in-depth interpretation of implicit feedback for individual users. Specifically, G-UBS operates via two key agents. First, the User Group Manager (UGM) effectively clusters users to generate group profiles utilizing a ``summarize-cluster-reflect" workflow based on LLMs. Second, the User Feedback Modeler (UFM) employs an innovative group-aware reinforcement learning approach, where each user is guided by the associated group profiles during the reinforcement learning process, allowing UFM to robustly and deeply examine the reasons behind implicit feedback. To assess our G-UBS paradigm, we have constructed a Video Recommendation benchmark with Implicit Feedback (IF-VR). To the best of our knowledge, this is the first multi-modal benchmark for implicit feedback evaluation in video recommendation, encompassing 15k users, 25k videos, and 933k interaction records with implicit feedback. Extensive experiments on IF-VR demonstrate that G-UBS significantly outperforms mainstream LLMs and MLLMs, with a 4.0% higher proportion of videos achieving a play rate > 30% and 14.9% higher reasoning accuracy on IF-VR.

Figures (5)

• Figure 1: Overview of our G-UBS paradigm: To better visualize implicit feedback, we integrate UGM-generated group profiles into the UFM training process.
• Figure 2: Overview of UGM group profile generation pipeline.
• Figure 3: Overview of UFM Reinforcement Learning Paradigm.
• Figure 4: Case Study of G-UBS.
• Figure 5: Visualization of IF-VR Dataset.