# Enhancing Recommender Systems with Large Language Model Reasoning Graphs

arXiv: https://arxiv.org/abs/2308.10835 · HTML: https://mlsanity.com/paper/2308.10835/

## Key facts

- Cited by 52 papers in the map (data through 14 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.

## Placed in

- LLM reasoning / [LLM reasoning for recommendation](https://mlsanity.com/lr/llm-reasoning-for-recommendation/)

## Builds on (most cited first, 4 of 4)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Language Models Can Improve Event Prediction by Few-Shot Abductive Reasoning](https://mlsanity.com/paper/2305.16646/) (2023)
- [Statler: State-Maintaining Language Models for Embodied Reasoning](https://mlsanity.com/paper/2306.17840/) (2023)

## Built on by (most cited first, 30 of 52)

- [Time-LLM: Time Series Forecasting by Reprogramming Large Language Models](https://mlsanity.com/paper/2310.01728/) (2023)
- [AgentCF: Collaborative Learning with Autonomous Language Agents for Recommender Systems](https://mlsanity.com/paper/2310.09233/) (2023)
- [Large Language Models for Education: A Survey](https://mlsanity.com/paper/2405.13001/) (2024)
- [A Survey on Medical Large Language Models: Technology, Application, Trustworthiness, and Future Directions](https://mlsanity.com/paper/2406.03712/) (2024)
- [DRDT: Dynamic Reflection with Divergent Thinking for LLM-based Sequential Recommendation](https://mlsanity.com/paper/2312.11336/) (2023)
- [Intelligent Virtual Assistants with LLM-based Process Automation](https://mlsanity.com/paper/2312.06677/) (2023)
- [Prompt-augmented Temporal Point Process for Streaming Event Sequence](https://mlsanity.com/paper/2310.04993/) (2023)
- [LLM-Enhanced User-Item Interactions: Leveraging Edge Information for Optimized Recommendations](https://mlsanity.com/paper/2402.09617/) (2024)
- [PrefillOnly: An Inference Engine for Prefill-only Workloads in Large Language Model Applications](https://mlsanity.com/paper/2505.07203/) (2025)
- [A Causal Explainable Guardrails for Large Language Models](https://mlsanity.com/paper/2405.04160/) (2024)
- [Sora Detector: A Unified Hallucination Detection for Large Text-to-Video Models](https://mlsanity.com/paper/2405.04180/) (2024)
- [A Survey of Foundation Model-Powered Recommender Systems: From Feature-Based, Generative to Agentic Paradigms](https://mlsanity.com/paper/2504.16420/) (2025)
- [Taxonomy-Guided Zero-Shot Recommendations with LLMs](https://mlsanity.com/paper/2406.14043/) (2024)
- [Exploring the Impact of Large Language Models on Recommender Systems: An Extensive Review](https://mlsanity.com/paper/2402.18590/) (2024)
- [Tri-Level Navigator: LLM-Empowered Tri-Level Learning for Time Series OOD Generalization](https://mlsanity.com/paper/2410.07018/) (2024)
- [Large Language Model with Graph Convolution for Recommendation](https://mlsanity.com/paper/2402.08859/) (2024)
- [Professional Agents -- Evolving Large Language Models into Autonomous Experts with Human-Level Competencies](https://mlsanity.com/paper/2402.03628/) (2024)
- [Data-Centric Financial Large Language Models](https://mlsanity.com/paper/2310.17784/) (2023)
- [AAD-LLM: Adaptive Anomaly Detection Using Large Language Models](https://mlsanity.com/paper/2411.00914/) (2024)
- [What Makes a Good Natural Language Prompt?](https://mlsanity.com/paper/2506.06950/) (2025)
- [Enhancing Collaborative Semantics of Language Model-Driven Recommendations via Graph-Aware Learning](https://mlsanity.com/paper/2406.13235/) (2024)
- [Inference Computation Scaling for Feature Augmentation in Recommendation Systems](https://mlsanity.com/paper/2502.16040/) (2025)
- [Graph Foundation Models for Recommendation: A Comprehensive Survey](https://mlsanity.com/paper/2502.08346/) (2025)
- [RAAD-LLM: Adaptive Anomaly Detection Using LLMs and RAG Integration](https://mlsanity.com/paper/2503.02800/) (2025)
- [Survey for Landing Generative AI in Social and E-commerce Recsys -- the Industry Perspectives](https://mlsanity.com/paper/2406.06475/) (2024)
- [Self-supervised Adaptive Pre-training of Multilingual Speech Models for Language and Dialect Identification](https://mlsanity.com/paper/2312.07338/) (2023)
- [LLM-KT: A Versatile Framework for Knowledge Transfer from Large Language Models to Collaborative Filtering](https://mlsanity.com/paper/2411.00556/) (2024)
- [AttnCache: Accelerating Self-Attention Inference for LLM Prefill via Attention Cache](https://mlsanity.com/paper/2510.25979/) (2025)
- [Verifiable Reasoning for LLM-based Generative Recommendation](https://mlsanity.com/paper/2603.07725/) (2026)
- [Prompt-Consistency Image Generation (PCIG): A Unified Framework Integrating LLMs, Knowledge Graphs, and Controllable Diffusion Models](https://mlsanity.com/paper/2406.16333/) (2024)

## 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.