mlsanityData to 7 Oct 2026

Enhancing Recommender Systems with Large Language Model Reasoning Graphs

arXiv 2308.10835 ↗First posted 21 Aug 2023cs.IRcited by 52

On the map: LLM reasoning → LLM reasoning for recommendation

Abstract (arXiv)

Recommendation systems aim to provide users with relevant suggestions, but often lack interpretability and fail to capture higher-level semantic relationships between user behaviors and profiles. In this paper, we propose a novel approach that leverages large language models (LLMs) to construct personalized reasoning graphs. These graphs link a user's profile and behavioral sequences through causal and logical inferences, representing the user's interests in an interpretable way. Our approach, LLM reasoning graphs (LLMRG), has four components: chained graph reasoning, divergent extension, self-verification and scoring, and knowledge base self-improvement. The resulting reasoning graph is encoded using graph neural networks, which serves as additional input to improve conventional recommender systems, without requiring extra user or item information. Our approach demonstrates how LLMs can enable more logical and interpretable recommender systems through personalized reasoning graphs. LLMRG allows recommendations to benefit from both engineered recommendation systems and LLM-derived reasoning graphs. We demonstrate the effectiveness of LLMRG on benchmarks and real-world scenarios in enhancing base recommendation models.

Key facts. Cited by 52 papers in the map (data through 7 Oct 2026). Placed in LLM reasoning for recommendation, one of 17 directions in LLM reasoning. Builds on 4 of its 44 references that are in the map. First posted on arXiv 21 Aug 2023.

Builds on

4 of 44 references.

References · 4

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  3. 2023Language Models Can Improve Event Prediction by Few-Shot Abductive Reasoningcited by 44
  4. 2023Statler: State-Maintaining Language Models for Embodied Reasoningcited by 40

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 11; 2024: 21; 2025: 16; 2026: 4.

52 papers.

Sort:

By area:

  1. 2023Time-LLM: Time Series Forecasting by Reprogramming Large Language Modelscited by 680
  2. 2023AgentCF: Collaborative Learning with Autonomous Language Agents for Recommender Systemscited by 116
  3. 2024A Survey on Medical Large Language Models: Technology, Application, Trustworthiness, and Future Directionscited by 34
  4. 2024Large Language Models for Education: A Surveycited by 32
  5. 2023DRDT: Dynamic Reflection with Divergent Thinking for LLM-based Sequential Recommendationcited by 27
  6. 2023Intelligent Virtual Assistants with LLM-based Process Automationcited by 26
  7. 2023Prompt-augmented Temporal Point Process for Streaming Event Sequencecited by 24
  8. 2024LLM-Enhanced User-Item Interactions: Leveraging Edge Information for Optimized Recommendationscited by 24
  9. 2025PrefillOnly: An Inference Engine for Prefill-only Workloads in Large Language Model Applicationscited by 21
  10. 2024A Causal Explainable Guardrails for Large Language Modelscited by 18
  11. 2024Sora Detector: A Unified Hallucination Detection for Large Text-to-Video Modelscited by 17
  12. 2025A Survey of Foundation Model-Powered Recommender Systems: From Feature-Based, Generative to Agentic Paradigmscited by 17
38 more
  1. 2024Taxonomy-Guided Zero-Shot Recommendations with LLMscited by 15
  2. 2024Tri-Level Navigator: LLM-Empowered Tri-Level Learning for Time Series OOD Generalizationcited by 12
  3. 2024Exploring the Impact of Large Language Models on Recommender Systems: An Extensive Reviewcited by 11
  4. 2024Large Language Model with Graph Convolution for Recommendationcited by 10
  5. 2024Professional Agents -- Evolving Large Language Models into Autonomous Experts with Human-Level Competenciescited by 9
  6. 2023Data-Centric Financial Large Language Modelscited by 8
  7. 2024AAD-LLM: Adaptive Anomaly Detection Using Large Language Modelscited by 7
  8. 2025What Makes a Good Natural Language Prompt?cited by 6
  9. 2024Enhancing Collaborative Semantics of Language Model-Driven Recommendations via Graph-Aware Learningcited by 5
  10. 2025Inference Computation Scaling for Feature Augmentation in Recommendation Systemscited by 5
  11. 2025RAAD-LLM: Adaptive Anomaly Detection Using LLMs and RAG Integrationcited by 4
  12. 2024Survey for Landing Generative AI in Social and E-commerce Recsys -- the Industry Perspectivescited by 3
  13. 2025Graph Foundation Models for Recommendation: A Comprehensive Surveycited by 3
  14. 2023Self-supervised Adaptive Pre-training of Multilingual Speech Models for Language and Dialect Identificationcited by 2
  15. 2024LLM-KT: A Versatile Framework for Knowledge Transfer from Large Language Models to Collaborative Filteringcited by 2
  16. 2025AttnCache: Accelerating Self-Attention Inference for LLM Prefill via Attention Cachecited by 2
  17. 2026Verifiable Reasoning for LLM-based Generative Recommendationcited by 2
  18. 2024Prompt-Consistency Image Generation (PCIG): A Unified Framework Integrating LLMs, Knowledge Graphs, and Controllable Diffusion Modelscited by 1
  19. 2025Trustworthy GNNs with LLMs: A Systematic Review and Taxonomycited by 1
  20. 2025Does Knowledge Distillation Matter for Large Language Model based Bundle Generation?cited by 1
  21. 2025DP-GPT4MTS: Dual-Prompt Large Language Model for Textual-Numerical Time Series Forecastingcited by 1
  22. 2025Routing Distilled Knowledge via Mixture of LoRA Experts for Large Language Model based Bundle Generationcited by 1
  23. 2025MGFRec: Towards Reinforced Reasoning Recommendation with Multiple Groundings and Feedbackcited by 1
  24. 2026Fine-Tuned LLM as a Complementary Predictor Improving Ads Systemcited by 1
  25. 2023Enhancing Asynchronous Time Series Forecasting with Contrastive Relational Inferencecited by 0
  26. 2023Enhancing Multilingual Speech Recognition through Language Prompt Tuning and Frame-Level Language Adaptercited by 0
  27. 2023GMTR: Graph Matching Transformerscited by 0
  28. 2023DarkShot: Lighting Dark Images with Low-Compute and High-Qualitycited by 0
  29. 2024TRLS: A Time Series Representation Learning Framework via Spectrogram for Medical Signal Processingcited by 0
  30. 2024TEN-GUARD: Tensor Decomposition for Backdoor Attack Detection in Deep Neural Networkscited by 0
  31. 2024T-Pixel2Mesh: Combining Global and Local Transformer for 3D Mesh Generation from a Single Imagecited by 0
  32. 2024Strategic Arms with Side Communication Prevail Over Low-Regret MAB Algorithmscited by 0
  33. 2024Towards General Deepfake Detection with Dynamic Curriculumcited by 0
  34. 2024Attr-Int: A Simple and Effective Entity Alignment Framework for Heterogeneous Knowledge Graphscited by 0
  35. 2025Mask6D: Masked Pose Priors For 6D Object Pose Estimationcited by 0
  36. 2025End-to-End Personalization: Unifying Recommender Systems with Large Language Modelscited by 0
  37. 2025HALO: Memory-Centric Heterogeneous Accelerator with 2.5D Integration for Low-Batch LLM Inferencecited by 0
  38. 2025CLLMRec: LLM-powered Cognitive-Aware Concept Recommendation via Semantic Alignment and Prerequisite Knowledge Distillationcited by 0

50 most cited of 52 All 52 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024LLM-Powered Explanations: Unraveling Recommendations Through Subgraph Reasoning
  2. 2025CORONA: A Coarse-to-Fine Framework for Graph-based Recommendation with Large Language Models
  3. 2024Leveraging LLM Reasoning Enhances Personalized Recommender Systems
  4. 2024ReasoningRec: Bridging Personalized Recommendations and Human-Interpretable Explanations through LLM Reasoning
  5. 2024LLM is Knowledge Graph Reasoner: LLM's Intuition-aware Knowledge Graph Reasoning for Cold-start Sequential Recommendation
  6. 2024LLM-Guided Multi-View Hypergraph Learning for Human-Centric Explainable Recommendation
  7. 2024Enhancing High-order Interaction Awareness in LLM-based Recommender Model
  8. 2023LLMRec: Large Language Models with Graph Augmentation for Recommendation