Bridging Personalization and Control in Scientific Personalized Search

2024-11-05

AI Summary

Personalized search often suffers from opaque mechanisms, leading to diminished user control and filter bubbles. This paper addresses scientific literature retrieval by proposing CtrlCE—a controllable cross-encoder model augmented with editable memory—and a calibration-based hybrid ranking mechanism, enabling users to explicitly and interactively edit historical memory for real-time personalization control. CtrlCE integrates an editable memory module into a cross-encoder architecture to support fine-grained intervention; the calibration hybrid model dynamically and interpretable decides—based on confidence scores—whether to apply personalization. Experiments across four scientific domains demonstrate significant improvements in retrieval effectiveness and result diversity. Calibration analysis validates the rationality of personalization triggering, while a user study confirms that memory editing substantially enhances perceived control and result satisfaction.

Technology Category

• Search and Optimization: Learning to Search
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Machine Learning: Learning Preferences or Rankings

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Applications of semantic technologies for improving search, browsing, recommendation, personalization

Abstract

Personalized search is a problem where models benefit from learning user preferences from per-user historical interaction data. The inferred preferences enable personalized ranking models to improve the relevance of documents for users. However, personalization is also seen as opaque in its use of historical interactions and is not amenable to users' control. Further, personalization limits the diversity of information users are exposed to. While search results may be automatically diversified this does little to address the lack of control over personalization. In response, we introduce a model for personalized search that enables users to control personalized rankings proactively. Our model, CtrlCE, is a novel cross-encoder model augmented with an editable memory built from users' historical interactions. The editable memory allows cross-encoders to be personalized efficiently and enables users to control personalized ranking. Next, because all queries do not require personalization, we introduce a calibrated mixing model which determines when personalization is necessary. This enables users to control personalization via their editable memory only when necessary. To thoroughly evaluate CtrlCE, we demonstrate its empirical performance in four domains of science, its ability to selectively request user control in a calibration evaluation of the mixing model, and the control provided by its editable memory in a user study.

Problem

• Balancing personalization and user control in search
• Addressing opacity and limited diversity in personalized results
• Enabling proactive user control over search rankings

Innovation

• Editable memory enables user-controlled personalized ranking
• Calibrated mixing model determines personalization necessity
• Cross-encoder model efficiently personalizes search results