mlsanityData to 7 Oct 2026

Reason4Rec: Deliberative User Preference Alignment of Large Language Models for Recommendation

arXiv 2502.02061 ↗First posted 4 Feb 2025cs.IRcited by 21

On the map: LLM reasoning → LLM reasoning for recommendation

Abstract (arXiv)

Aligning Large Language Models (LLMs) with recommendation tasks represents an emerging paradigm in recommendation domain, exhibiting promising performance overall. However, these aligned recommendation LLMs often struggle with complex scenarios due to limitations in the current alignment task formulation, which optimizes LLMs to directly generate user feedback without deliberation. To develop more reliable recommendation LLMs, we introduce a new textitDeliberative Recommendation task, which enforces explicit reasoning about user preferences as an additional alignment objective. To address this task, we propose a textitReasoning-powered Recommender framework designed to enhance reasoning capabilities by leveraging verbalized user feedback in a step-wise manner. Specifically, this framework employs collaborative step-wise experts alongside specifically crafted expert-wise training strategies. Extensive experiments conducted on three real-world datasets demonstrate the rationality of the deliberative task formulation and the effectiveness of the proposed framework in improving both prediction accuracy and reasoning quality. Our implementation is publicly available on GitHub: https://github.com/Peter-Fy/Reason4Rec.

Key facts. Cited by 21 papers in the map (data through 7 Oct 2026). Placed in LLM reasoning for recommendation, one of 17 directions in LLM reasoning. Builds on 9 of its 63 references that are in the map. First posted on arXiv 4 Feb 2025.

Builds on

9 of 63 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024Leveraging LLM Reasoning Enhances Personalized Recommender Systems22 Jul
  2. 2024Can Small Language Models be Good Reasoners for Sequential Recommendation?7 Mar

Other references · 7

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  2. 2024Deliberative Alignment: Reasoning Enables Safer Language Modelscited by 292
  3. 2024Large Language Models for Mathematical Reasoning: Progresses and Challengescited by 283
  4. 2023MathPrompter: Mathematical Reasoning using Large Language Modelscited by 236
  5. 2024Faithful Logical Reasoning via Symbolic Chain-of-Thoughtcited by 99
  6. 2024Q*: Improving Multi-step Reasoning for LLMs with Deliberative Planningcited by 95
  7. 2025Think More, Hallucinate Less: Mitigating Hallucinations via Dual Process of Fast and Slow Thinkingcited by 29

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 8; 2026: 13.

21 papers.

Sort:

By area:

  1. 2025Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Modelscited by 381
  2. 2025Reinforced Latent Reasoning for LLM-based Recommendationcited by 46
  3. 2025OnePiece: Bringing Context Engineering and Reasoning to Industrial Cascade Ranking Systemcited by 18
  4. 2025Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challengescited by 14
  5. 2025R2ec: Towards Large Recommender Models with Reasoningcited by 13
  6. 2026Reasoning over Semantic IDs Enhances Generative Recommendationcited by 12
  7. 2026Why Thinking Hurts: Diagnosing and Rectifying Linguistic Inertia in Large Language Models for Recommendationcited by 9
  8. 2026Factorized Latent Reasoning for LLM-based Recommendationcited by 3
  9. 2025HADSF: Aspect Aware Semantic Control for Explainable Recommendationcited by 2
  10. 2025MGFRec: Towards Reinforced Reasoning Recommendation with Multiple Groundings and Feedbackcited by 1
  11. 2025Token-Controlled Re-ranking for Sequential Recommendation via LLMscited by 1
  12. 2026R3-REC: Reasoning-Driven Recommendation via Retrieval-Augmented LLMs over Multi-Granular Interest Signalscited by 1
9 more
  1. 2026LASAR: Latent Adaptive Semantic Aligned Reasoning for Generative Recommendationcited by 1
  2. 2026AgenticRec: A Recommendation-Oriented Agentic Framework with Progressive Tool-Integrated Reasoning Optimizationcited by 0
  3. 2026User Simulator-Guided Multi-Turn Preference Optimization for Reasoning LLM-based Conversational Recommendationcited by 0
  4. 2026RRCM: Ranking-Driven Retrieval over Collaborative and Meta Memories for LLM Recommendationcited by 0
  5. 2026Intuition-Guided Latent Reasoning for LLM-Based Recommendationcited by 0
  6. 2026WhisperRec: Latent Reasoning for Efficient Foundation Recommendation Modelscited by 0
  7. 2026Towards Efficient Reasoning in LLM-Based Recommender Systems via Model Mergingcited by 0
  8. 2026SelfDR: Self-Distillation from Reasoning for LLM-Based Recommendationcited by 0
  9. 2026TATK: Triple-Aware Top-K Learning with Knowledge-Grounded Verification for LLM-based Sequential Recommendationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024ReasoningRec: Bridging Personalized Recommendations and Human-Interpretable Explanations through LLM Reasoning
  2. 2024Aligning Large Language Models for Controllable Recommendations
  3. 2026Toward User Preference Alignment in LLM Recommendation via Explicit Context Feedback
  4. 2025Generative Reasoning Recommendation via LLMs
  5. 2026From Prompting to Behavioral Alignment: Personalized LLM Judges for Recommendation Evaluation
  6. 2023RecExplainer: Aligning Large Language Models for Explaining Recommendation Models
  7. 2025User Feedback Alignment for LLM-powered Exploration in Large-scale Recommendation Systems
  8. 2024LANE: Logic Alignment of Non-tuning Large Language Models and Online Recommendation Systems for Explainable Reason Generation