mlsanityData to 7 Oct 2026

CoRAL: Collaborative Retrieval-Augmented Large Language Models Improve Long-tail Recommendation

arXiv 2403.06447 ↗First posted 11 Mar 2024cs.IR cs.AIcited by 44

On the map: LLM reasoning → LLM reasoning for recommendation

also in 1 more
Abstract (arXiv)

The long-tail recommendation is a challenging task for traditional recommender systems, due to data sparsity and data imbalance issues. The recent development of large language models (LLMs) has shown their abilities in complex reasoning, which can help to deduce users' preferences based on very few previous interactions. However, since most LLM-based systems rely on items' semantic meaning as the sole evidence for reasoning, the collaborative information of user-item interactions is neglected, which can cause the LLM's reasoning to be misaligned with task-specific collaborative information of the dataset. To further align LLMs' reasoning to task-specific user-item interaction knowledge, we introduce collaborative retrieval-augmented LLMs, CoRAL, which directly incorporate collaborative evidence into the prompts. Based on the retrieved user-item interactions, the LLM can analyze shared and distinct preferences among users, and summarize the patterns indicating which types of users would be attracted by certain items. The retrieved collaborative evidence prompts the LLM to align its reasoning with the user-item interaction patterns in the dataset. However, since the capacity of the input prompt is limited, finding the minimally-sufficient collaborative information for recommendation tasks can be challenging. We propose to find the optimal interaction set through a sequential decision-making process and develop a retrieval policy learned through a reinforcement learning (RL) framework, CoRAL. Our experimental results show that CoRAL can significantly improve LLMs' reasoning abilities on specific recommendation tasks. Our analysis also reveals that CoRAL can more efficiently explore collaborative information through reinforcement learning.

Key facts. Cited by 44 papers in the map (data through 7 Oct 2026). Placed in LLM reasoning for recommendation, one of 17 directions in LLM reasoning. Builds on 39 of its 75 references that are in the map. First posted on arXiv 11 Mar 2024.

Builds on

39 of 75 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023DRDT: Dynamic Reflection with Divergent Thinking for LLM-based Sequential Recommendation18 Dec

Other references · 38

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2017Proximal Policy Optimization Algorithmscited by 14,441
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  4. 2015Continuous control with deep reinforcement learningcited by 3,279
  5. 2013Playing Atari with Deep Reinforcement Learningcited by 3,211
  6. 2016Wide & Deep Learning for Recommender Systemscited by 745
  7. 2020Long-tail learning via logit adjustmentcited by 605
  8. 2017Deep & Cross Network for Ad Click Predictionscited by 392
  9. 2023TALLRec: An Effective and Efficient Tuning Framework to Align Large Language Model with Recommendationcited by 336
  10. 2018What is the Effect of Importance Weighting in Deep Learning?cited by 250
  11. 2016Recommendations as Treatments: Debiasing Learning and Evaluationcited by 246
  12. 2023Adapting Large Language Models by Integrating Collaborative Semantics for Recommendationcited by 171
26 more
  1. 2023Representation Learning with Large Language Models for Recommendationcited by 155
  2. 2017Attentional Factorization Machines: Learning the Weight of Feature Interactions via Attention Networkscited by 126
  3. 2023Do LLMs Understand User Preferences? Evaluating LLMs On User Rating Predictioncited by 113
  4. 2023CoLLM: Integrating Collaborative Embeddings into Large Language Models for Recommendationcited by 99
  5. 2020Model-Agnostic Counterfactual Reasoning for Eliminating Popularity Bias in Recommender Systemcited by 94
  6. 2017Causal Embeddings for Recommendationcited by 79
  7. 2023Leveraging Large Language Models for Sequential Recommendationcited by 78
  8. 2023Can ChatGPT Replace Traditional KBQA Models? An In-depth Analysis of the Question Answering Performance of the GPT LLM Familycited by 71
  9. 2023Large Language Models are Competitive Near Cold-start Recommenders for Language- and Item-based Preferencescited by 66
  10. 2023Collaborative Large Language Model for Recommender Systemscited by 63
  11. 2024InstructGraph: Boosting Large Language Models via Graph-centric Instruction Tuning and Preference Alignmentcited by 56
  12. 2023Knowledge-Augmented Large Language Models for Personalized Contextual Query Suggestioncited by 43
  13. 2020A Model of Two Tales: Dual Transfer Learning Framework for Improved Long-tail Item Recommendationcited by 38
  14. 2021User-centered Evaluation of Popularity Bias in Recommender Systemscited by 38
  15. 2020Correcting for Selection Bias in Learning-to-rank Systemscited by 35
  16. 2020Long-tail Session-based Recommendationcited by 33
  17. 2019Improving Generative Visual Dialog by Answering Diverse Questionscited by 21
  18. 2021Correcting Exposure Bias for Link Recommendationcited by 17
  19. 2023Knowledge Plugins: Enhancing Large Language Models for Domain-Specific Recommendationscited by 16
  20. 2022Experiments on Generalizability of User-Oriented Fairness in Recommender Systemscited by 13
  21. 2023Large Language Models are Not Stable Recommender Systemscited by 13
  22. 2022Empowering Long-tail Item Recommendation through Cross Decoupling Network (CDN)cited by 12
  23. 2021Leave No User Behind: Towards Improving the Utility of Recommender Systems for Non-mainstream Userscited by 11
  24. 2020Modeling and Counteracting Exposure Bias in Recommender Systemscited by 7
  25. 2021Reenvisioning Collaborative Filtering vs Matrix Factorizationcited by 6
  26. 2023Bridging the Information Gap Between Domain-Specific Model and General LLM for Personalized Recommendationcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 29; 2026: 11.

44 papers.

Sort:

By area:

  1. 2024A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Modelscited by 450
  2. 2025Knowledge Graph Retrieval-Augmented Generation for LLM-based Recommendationcited by 56
  3. 2024A Survey on Data Synthesis and Augmentation for Large Language Modelscited by 40
  4. 2024Towards Next-Generation LLM-based Recommender Systems: A Survey and Beyondcited by 26
  5. 2025Towards Agentic Recommender Systems in the Era of Multimodal Large Language Modelscited by 25
  6. 2025Can Compressed LLMs Truly Act? An Empirical Evaluation of Agentic Capabilities in LLM Compressioncited by 15
  7. 2025DrunkAgent: Stealthy Memory Corruption in LLM-Powered Recommender Agentscited by 12
  8. 2025ARAG: Agentic Retrieval Augmented Generation for Personalized Recommendationcited by 12
  9. 2025Graph Retrieval-Augmented LLM for Conversational Recommendation Systemscited by 10
  10. 2025In-context Ranking Preference Optimizationcited by 9
  11. 2025Lost in Sequence: Do Large Language Models Understand Sequential Recommendation?cited by 8
  12. 2025Retrieval-Augmented Purifier for Robust LLM-Empowered Recommendationcited by 7
32 more
  1. 2025Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Modelscited by 7
  2. 2025AGRAG: Advanced Graph-based Retrieval-Augmented Generation for LLMscited by 7
  3. 2026AMEM4Rec: Leveraging Cross-User Similarity for Memory Evolution in Agentic LLM Recommenderscited by 7
  4. 2025TAMEing Long Contexts in Personalization: Towards Training-Free and State-Aware MLLM Personalized Assistantcited by 6
  5. 2024Enhancing Tourism Recommender Systems for Sustainable City Trips Using Retrieval-Augmented Generationcited by 4
  6. 2025Field Matters: A Lightweight LLM-enhanced Method for CTR Predictioncited by 4
  7. 2025KERAG_R: Knowledge-Enhanced Retrieval-Augmented Generation for Recommendationcited by 3
  8. 2025A Comprehensive Review on Harnessing Large Language Models to Overcome Recommender System Challengescited by 3
  9. 2025AgentDR: Dynamic Recommendation with Implicit Item-Item Relations via LLM-based Agentscited by 3
  10. 2026Autonomous Information Seeking: A Roadmap for Agentic Recommender Systemscited by 3
  11. 2025Geography-Aware Large Language Models for Next POI Recommendationcited by 2
  12. 2025Tuning Language Models for Robust Prediction of Diverse User Behaviorscited by 2
  13. 2025LLMs for Supply Chain Managementcited by 2
  14. 2025Learning to Shop Like Humans: A Review-driven Retrieval-Augmented Recommendation Framework with LLMscited by 2
  15. 2025WebRec: Enhancing LLM-based Recommendations with Attention-guided RAG from Webcited by 2
  16. 2025ItemRAG: Item-Based Retrieval-Augmented Generation for LLM-Based Recommendationcited by 2
  17. 2026Retrieval Augmented Conversational Recommendation with Reinforcement Learningcited by 2
  18. 2025AdaptRec: A Self-Adaptive Framework for Sequential Recommendations with Large Language Modelscited by 1
  19. 2025Tuning-Free LLM Can Build A Strong Recommender Under Sparse Connectivity And Knowledge Gap Via Extracting Intentcited by 1
  20. 2026Skill-CMIB: Multimodal Agent Skill for Consistent Action via Conditional Multimodal Information Bottleneckcited by 1
  21. 2025Improving LLM Interpretability and Performance via Guided Embedding Refinement for Sequential Recommendationcited by 0
  22. 2025FB-RAG: Improving RAG with Forward and Backward Lookupcited by 0
  23. 2025Retrieval-Confused Generation is a Good Defender for Privacy Violation Attack of Large Language Modelscited by 0
  24. 2025VoteGCL: Enhancing Graph-based Recommendations with Majority-Voting LLM-Rerank Augmentationcited by 0
  25. 2025EGRA:Toward Enhanced Behavior Graphs and Representation Alignment for Multimodal Recommendationcited by 0
  26. 2026Who Does What? Archetypes of Roles Assigned to LLMs During Human-AI Decision-Makingcited by 0
  27. 2026Adaptive Data Augmentation with Multi-armed Bandit: Sample-Efficient Embedding Calibration for Implicit Pattern Recognitioncited by 0
  28. 2026Taming the Long Tail: Efficient Item-wise Sharpness-Aware Minimization for LLM-based Recommender Systemscited by 0
  29. 2026Retrieve-then-Adapt: Retrieval-Augmented Test-Time Adaptation for Sequential Recommendationcited by 0
  30. 2026A Graph-Enhanced Defense Framework for Explainable Fake News Detection with LLMcited by 0
  31. 2026CoPA: Benchmarking Personalized Question Answering with Data-Informed Cognitive Factorscited by 0
  32. 2026BAHSD: Bridging the Long-tail Gap via Adaptive Distillation in Black-box Sequential Recommendationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026RRCM: Ranking-Driven Retrieval over Collaborative and Meta Memories for LLM Recommendation
  2. 2024Large Language Models Enhanced Collaborative Filtering
  3. 2024LLM-ESR: Large Language Models Enhancement for Long-tailed Sequential Recommendation
  4. 2025Do LLMs Understand Collaborative Signals? Diagnosis and Repair
  5. 2025Bridging Collaborative Filtering and Large Language Models with Dynamic Alignment, Multimodal Fusion and Evidence-grounded Explanations
  6. 2024Aligning Large Language Models with Recommendation Knowledge
  7. 2025LLMs as Better Recommenders with Natural Language Collaborative Signals: A Self-Assessing Retrieval Approach
  8. 2023How Can Recommender Systems Benefit from Large Language Models: A Survey