mlsanityData to 14 Oct 2026

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

arXiv 2602.12968 ↗First posted 13 Feb 2026cs.IR cs.AI cs.CLcited by 0

On the map: LLM reasoning → LLM reasoning for recommendation

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in LLM reasoning for recommendation, one of 17 directions in LLM reasoning. Builds on 19 of its 47 references that are in the map. First posted on arXiv 13 Feb 2026.

Builds on

19 of 47 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025Align3GR: Unified Multi-Level Alignment for LLM-based Generative Recommendation14 Nov
  2. 2025OnePiece: Bringing Context Engineering and Reasoning to Industrial Cascade Ranking System22 Sep

Other references · 17

  1. 2022Training language models to follow instructions with human feedbackcited by 15,971
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  3. 2025Qwen3 Technical Reportcited by 8,820
  4. 2024Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendationscited by 188
  5. 2025OneRec: Unifying Retrieve and Rank with Generative Recommender and Iterative Preference Alignmentcited by 173
  6. 2024On Softmax Direct Preference Optimization for Recommendationcited by 64
  7. 2024HLLM: Enhancing Sequential Recommendations via Hierarchical Large Language Models for Item and User Modelingcited by 63
  8. 2025OneTrans: Unified Feature Interaction and Sequence Modeling with One Transformer in Industrial Recommendercited by 35
  9. 2025Rec-R1: Bridging Generative Large Language Models and User-Centric Recommendation Systems via Reinforcement Learningcited by 33
  10. 2023Improving Generalization of Alignment with Human Preferences through Group Invariant Learningcited by 25
  11. 2025RecGPT Technical Reportcited by 11
  12. 2024A Text is Worth Several Tokens: Text Embedding from LLMs Secretly Aligns Well with The Key Tokenscited by 8
5 more
  1. 2025RecGPT-V2 Technical Reportcited by 8
  2. 2026HyFormer: Revisiting the Roles of Sequence Modeling and Feature Interaction in CTR Predictioncited by 6
  3. 2025Each Prompt Matters: Scaling Reinforcement Learning Without Wasting Rollouts on Hundred-Billion-Scale MoEcited by 2
  4. 2025Resource-Efficient Adaptation of Large Language Models for Text Embeddings via Prompt Engineering and Contrastive Fine-tuningcited by 1
  5. 2025HoMer: Addressing Heterogeneities by Modeling Sequential and Set-wise Contexts for CTR Predictioncited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026From Prompting to Behavioral Alignment: Personalized LLM Judges for Recommendation Evaluation
  2. 2025R1-Ranker: Teaching LLM Rankers to Reason
  3. 2024Aligning Large Language Models for Controllable Recommendations
  4. 2026Reasoning to Rank: An End-to-End Solution for Exploiting Large Language Models for Recommendation
  5. 2026Reinforced Preference Optimization for Reasoning-Augmented Recommendations
  6. 2023RecExplainer: Aligning Large Language Models for Explaining Recommendation Models
  7. 2026QueryAgent-R1: Bridging Query Generation and Product Retrieval for E-Commerce Query Recommendation
  8. 2025Generative Reasoning Recommendation via LLMs