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

arXiv: https://arxiv.org/abs/2403.06447 · HTML: https://mlsanity.com/paper/2403.06447/

## Key facts

- Cited by 44 papers in the map (data through 14 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.

## Placed in

- LLM reasoning / [LLM reasoning for recommendation](https://mlsanity.com/lr/llm-reasoning-for-recommendation/)
- Retrieval-augmented generation / [RAG for recommendation](https://mlsanity.com/rag/rag-for-recommendation/)

## Builds on (most cited first, 30 of 39)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Continuous control with deep reinforcement learning](https://mlsanity.com/paper/1509.02971/) (2015)
- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [Wide & Deep Learning for Recommender Systems](https://mlsanity.com/paper/1606.07792/) (2016)
- [Long-tail learning via logit adjustment](https://mlsanity.com/paper/2007.07314/) (2020)
- [Deep & Cross Network for Ad Click Predictions](https://mlsanity.com/paper/1708.05123/) (2017)
- [TALLRec: An Effective and Efficient Tuning Framework to Align Large Language Model with Recommendation](https://mlsanity.com/paper/2305.00447/) (2023)
- [What is the Effect of Importance Weighting in Deep Learning?](https://mlsanity.com/paper/1812.03372/) (2018)
- [Recommendations as Treatments: Debiasing Learning and Evaluation](https://mlsanity.com/paper/1602.05352/) (2016)
- [Adapting Large Language Models by Integrating Collaborative Semantics for Recommendation](https://mlsanity.com/paper/2311.09049/) (2023)
- [Representation Learning with Large Language Models for Recommendation](https://mlsanity.com/paper/2310.15950/) (2023)
- [Attentional Factorization Machines: Learning the Weight of Feature Interactions via Attention Networks](https://mlsanity.com/paper/1708.04617/) (2017)
- [Do LLMs Understand User Preferences? Evaluating LLMs On User Rating Prediction](https://mlsanity.com/paper/2305.06474/) (2023)
- [CoLLM: Integrating Collaborative Embeddings into Large Language Models for Recommendation](https://mlsanity.com/paper/2310.19488/) (2023)
- [Model-Agnostic Counterfactual Reasoning for Eliminating Popularity Bias in Recommender System](https://mlsanity.com/paper/2010.15363/) (2020)
- [Causal Embeddings for Recommendation](https://mlsanity.com/paper/1706.07639/) (2017)
- [Leveraging Large Language Models for Sequential Recommendation](https://mlsanity.com/paper/2309.09261/) (2023)
- [Can ChatGPT Replace Traditional KBQA Models? An In-depth Analysis of the Question Answering Performance of the GPT LLM Family](https://mlsanity.com/paper/2303.07992/) (2023)
- [Large Language Models are Competitive Near Cold-start Recommenders for Language- and Item-based Preferences](https://mlsanity.com/paper/2307.14225/) (2023)
- [Collaborative Large Language Model for Recommender Systems](https://mlsanity.com/paper/2311.01343/) (2023)
- [InstructGraph: Boosting Large Language Models via Graph-centric Instruction Tuning and Preference Alignment](https://mlsanity.com/paper/2402.08785/) (2024)
- [Knowledge-Augmented Large Language Models for Personalized Contextual Query Suggestion](https://mlsanity.com/paper/2311.06318/) (2023)
- [A Model of Two Tales: Dual Transfer Learning Framework for Improved Long-tail Item Recommendation](https://mlsanity.com/paper/2010.15982/) (2020)
- [User-centered Evaluation of Popularity Bias in Recommender Systems](https://mlsanity.com/paper/2103.06364/) (2021)
- [Correcting for Selection Bias in Learning-to-rank Systems](https://mlsanity.com/paper/2001.11358/) (2020)
- [Long-tail Session-based Recommendation](https://mlsanity.com/paper/2007.12329/) (2020)
- [DRDT: Dynamic Reflection with Divergent Thinking for LLM-based Sequential Recommendation](https://mlsanity.com/paper/2312.11336/) (2023)
- [Improving Generative Visual Dialog by Answering Diverse Questions](https://mlsanity.com/paper/1909.10470/) (2019)

## Built on by (most cited first, 30 of 44)

- [A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models](https://mlsanity.com/paper/2405.06211/) (2024)
- [Knowledge Graph Retrieval-Augmented Generation for LLM-based Recommendation](https://mlsanity.com/paper/2501.02226/) (2025)
- [A Survey on Data Synthesis and Augmentation for Large Language Models](https://mlsanity.com/paper/2410.12896/) (2024)
- [Towards Next-Generation LLM-based Recommender Systems: A Survey and Beyond](https://mlsanity.com/paper/2410.19744/) (2024)
- [Towards Agentic Recommender Systems in the Era of Multimodal Large Language Models](https://mlsanity.com/paper/2503.16734/) (2025)
- [Can Compressed LLMs Truly Act? An Empirical Evaluation of Agentic Capabilities in LLM Compression](https://mlsanity.com/paper/2505.19433/) (2025)
- [DrunkAgent: Stealthy Memory Corruption in LLM-Powered Recommender Agents](https://mlsanity.com/paper/2503.23804/) (2025)
- [ARAG: Agentic Retrieval Augmented Generation for Personalized Recommendation](https://mlsanity.com/paper/2506.21931/) (2025)
- [Graph Retrieval-Augmented LLM for Conversational Recommendation Systems](https://mlsanity.com/paper/2503.06430/) (2025)
- [In-context Ranking Preference Optimization](https://mlsanity.com/paper/2504.15477/) (2025)
- [Lost in Sequence: Do Large Language Models Understand Sequential Recommendation?](https://mlsanity.com/paper/2502.13909/) (2025)
- [Retrieval-Augmented Purifier for Robust LLM-Empowered Recommendation](https://mlsanity.com/paper/2504.02458/) (2025)
- [Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models](https://mlsanity.com/paper/2509.03036/) (2025)
- [AGRAG: Advanced Graph-based Retrieval-Augmented Generation for LLMs](https://mlsanity.com/paper/2511.05549/) (2025)
- [AMEM4Rec: Leveraging Cross-User Similarity for Memory Evolution in Agentic LLM Recommenders](https://mlsanity.com/paper/2602.08837/) (2026)
- [TAMEing Long Contexts in Personalization: Towards Training-Free and State-Aware MLLM Personalized Assistant](https://mlsanity.com/paper/2512.21616/) (2025)
- [Enhancing Tourism Recommender Systems for Sustainable City Trips Using Retrieval-Augmented Generation](https://mlsanity.com/paper/2409.18003/) (2024)
- [Field Matters: A Lightweight LLM-enhanced Method for CTR Prediction](https://mlsanity.com/paper/2505.14057/) (2025)
- [Autonomous Information Seeking: A Roadmap for Agentic Recommender Systems](https://mlsanity.com/paper/2607.04433/) (2026)
- [LLMs for Supply Chain Management](https://mlsanity.com/paper/2505.18597/) (2025)
- [KERAG_R: Knowledge-Enhanced Retrieval-Augmented Generation for Recommendation](https://mlsanity.com/paper/2507.05863/) (2025)
- [A Comprehensive Review on Harnessing Large Language Models to Overcome Recommender System Challenges](https://mlsanity.com/paper/2507.21117/) (2025)
- [AgentDR: Dynamic Recommendation with Implicit Item-Item Relations via LLM-based Agents](https://mlsanity.com/paper/2510.05598/) (2025)
- [Retrieval Augmented Conversational Recommendation with Reinforcement Learning](https://mlsanity.com/paper/2604.04457/) (2026)
- [Geography-Aware Large Language Models for Next POI Recommendation](https://mlsanity.com/paper/2505.13526/) (2025)
- [Tuning Language Models for Robust Prediction of Diverse User Behaviors](https://mlsanity.com/paper/2505.17682/) (2025)
- [Learning to Shop Like Humans: A Review-driven Retrieval-Augmented Recommendation Framework with LLMs](https://mlsanity.com/paper/2509.00698/) (2025)
- [WebRec: Enhancing LLM-based Recommendations with Attention-guided RAG from Web](https://mlsanity.com/paper/2511.14182/) (2025)
- [ItemRAG: Item-Based Retrieval-Augmented Generation for LLM-Based Recommendation](https://mlsanity.com/paper/2511.15141/) (2025)
- [AdaptRec: A Self-Adaptive Framework for Sequential Recommendations with Large Language Models](https://mlsanity.com/paper/2504.08786/) (2025)

## 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.