CTR-Guided Generative Query Suggestion in Conversational Search

2025-07-05

AI Summary

Generative query suggestion in conversational search suffers from sparse and noisy click signals, hindering accurate user preference modeling. To address this, we propose CTR-Weighted Direct Preference Optimization (CTR-DPO), a unified framework jointly optimizing click-through rate (CTR) estimation and generative query suggestion. First, we construct and calibrate a multi-source CTR model. Second, we design a diversity-aware preference alignment mechanism that explicitly balances relevance and semantic diversity during optimization. Third, we iteratively refine the generative model via CTR-guided calibration. Evaluated on two real-world conversational search benchmarks, CTR-DPO consistently outperforms strong baselines across three key metrics: CTR, human-rated relevance, and suggestion diversity. Our results empirically validate the effectiveness of co-modeling implicit user behavior (via CTR) and explicit generation preferences (via preference optimization) for improving conversational query suggestion.

Technology Category

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

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Generating effective query suggestions in conversational search requires aligning model outputs with user preferences, which is challenging due to sparse and noisy click signals. We propose GQS, a generative framework that integrates click modeling and preference optimization to enhance real-world user engagement. GQS consists of three key components: (1) a Multi-Source CTR Modeling module that captures diverse contextual signals to estimate fine-grained click-through rates; (2) a Diversity-Aware Preference Alignment strategy using CTR-weighted Direct Preference Optimization (DPO), which balances relevance and semantic diversity; and (3) a CTR-Calibrated Iterative Optimization process that jointly refines the CTR and generation models across training rounds. Experiments on two real-world tasks demonstrate that GQS outperforms strong baselines in CTR, relevance, and diversity.

Problem

• Align generative query suggestions with user preferences
• Address sparse noisy click signals in conversational search
• Balance relevance diversity in CTR-guided query generation

Innovation

• Multi-Source CTR Modeling captures contextual signals
• Diversity-Aware Preference Alignment balances relevance and diversity
• CTR-Calibrated Iterative Optimization refines models jointly