RGAlign-Rec: Ranking-Guided Alignment for Latent Query Reasoning in Recommendation Systems

TL;DR

This paper introduces RGAlign-Rec, a novel framework that aligns semantic reasoning with ranking objectives in recommendation systems, improving proactive intent prediction and recommendation accuracy through a multi-stage training paradigm validated on large-scale industrial data.

Contribution

The paper proposes a ranking-guided alignment framework combining an LLM-based reasoner with a ranking model, and introduces a multi-stage training process to enhance latent reasoning for better recommendations.

Findings

Achieves 0.12% GAUC gain on industrial dataset

Reduces error rate by 3.52% relative

Improves CTR by 0.98% in online A/B tests

Abstract

Proactive intent prediction is a critical capability in modern e-commerce chatbots, enabling "zero-query" recommendations by anticipating user needs from behavioral and contextual signals. However, existing industrial systems face two fundamental challenges: (1) the semantic gap between discrete user features and the semantic intents within the chatbot's Knowledge Base, and (2) the objective misalignment between general-purpose LLM outputs and task-specific ranking utilities. To address these issues, we propose RGAlign-Rec, a closed-loop alignment framework that integrates an LLM-based semantic reasoner with a Query-Enhanced (QE) ranking model. We also introduce Ranking-Guided Alignment (RGA), a multi-stage training paradigm that utilizes downstream ranking signals as feedback to refine the LLM's latent reasoning. Extensive experiments on a large-scale industrial dataset from Shopee demonstrate that RGAlign-Rec achieves a 0.12% gain in GAUC, leading to a significant 3.52% relative reduction in error rate, and a 0.56% improvement in Recall@3. Online A/B testing further validates the cumulative effectiveness of our framework: the Query-Enhanced model (QE-Rec) initially yields a 0.98% improvement in CTR, while the subsequent Ranking-Guided Alignment stage contributes an additional 0.13% gain. These results indicate that ranking-aware alignment effectively synchronizes semantic reasoning with ranking objectives, significantly enhancing both prediction accuracy and service quality in real-world proactive recommendation systems.