Enregistré dans:
Détails bibliographiques
Auteurs principaux: Liu, Junhua, Jihao, Yang, Chang, Cheng, LI, Kunrong, Fu, Bin, Lim, Kwan Hui
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2602.12968
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914328385421312
author Liu, Junhua
Jihao, Yang
Chang, Cheng
LI, Kunrong
Fu, Bin
Lim, Kwan Hui
author_facet Liu, Junhua
Jihao, Yang
Chang, Cheng
LI, Kunrong
Fu, Bin
Lim, Kwan Hui
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2602_12968
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle RGAlign-Rec: Ranking-Guided Alignment for Latent Query Reasoning in Recommendation Systems
Liu, Junhua
Jihao, Yang
Chang, Cheng
LI, Kunrong
Fu, Bin
Lim, Kwan Hui
Information Retrieval
Artificial Intelligence
Computation and Language
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.
title RGAlign-Rec: Ranking-Guided Alignment for Latent Query Reasoning in Recommendation Systems
topic Information Retrieval
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2602.12968