mlsanityData to 14 Oct 2026

Leveraging Large Language Models in Conversational Recommender Systems

arXiv 2305.07961 ↗First posted 13 May 2023cs.IR cs.CL cs.LGcited by 63

Not on the map. Why?

Abstract (arXiv)

A Conversational Recommender System (CRS) offers increased transparency and control to users by enabling them to engage with the system through a real-time multi-turn dialogue. Recently, Large Language Models (LLMs) have exhibited an unprecedented ability to converse naturally and incorporate world knowledge and common-sense reasoning into language understanding, unlocking the potential of this paradigm. However, effectively leveraging LLMs within a CRS introduces new technical challenges, including properly understanding and controlling a complex conversation and retrieving from external sources of information. These issues are exacerbated by a large, evolving item corpus and a lack of conversational data for training. In this paper, we provide a roadmap for building an end-to-end large-scale CRS using LLMs. In particular, we propose new implementations for user preference understanding, flexible dialogue management and explainable recommendations as part of an integrated architecture powered by LLMs. For improved personalization, we describe how an LLM can consume interpretable natural language user profiles and use them to modulate session-level context. To overcome conversational data limitations in the absence of an existing production CRS, we propose techniques for building a controllable LLM-based user simulator to generate synthetic conversations. As a proof of concept we introduce RecLLM, a large-scale CRS for YouTube videos built on LaMDA, and demonstrate its fluency and diverse functionality through some illustrative example conversations.

Key facts. Cited by 63 papers in the map (data through 14 Oct 2026). Builds on 81 of its 118 references that are in the map. First posted on arXiv 13 May 2023.

Builds on

81 of 118 references.

References · 81

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2022Training language models to follow instructions with human feedbackcited by 15,971
  4. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  5. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  6. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  7. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  8. 2022Generative Adversarial Networkscited by 5,627
  9. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
  10. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,375
  11. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,795
  12. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,720
38 more
  1. 2020Learning to summarize from human feedbackcited by 2,588
  2. 2022Emergent Abilities of Large Language Modelscited by 2,512
  3. 2022Survey of Hallucination in Natural Language Generationcited by 2,075
  4. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,745
  5. 2017Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)cited by 1,319
  6. 2021Improving language models by retrieving from trillions of tokenscited by 1,293
  7. 2022LaMDA: Language Models for Dialog Applicationscited by 1,220
  8. 2021Ethical and social risks of harm from Language Modelscited by 966
  9. 2020Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrievalcited by 849
  10. 2018Personalizing Dialogue Agents: I have a dog, do you have pets too?cited by 828
  11. 2021Retrieval Augmentation Reduces Hallucination in Conversationcited by 692
  12. 2022Large Language Models Can Self-Improvecited by 664
  13. 2014Neural Turing Machinescited by 644
  14. 2021Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigmcited by 606
  15. 2022Towards Reasoning in Large Language Models: A Surveycited by 596
  16. 2022Improving alignment of dialogue agents via targeted human judgementscited by 531
  17. 2021Large Dual Encoders Are Generalizable Retrieverscited by 456
  18. 2019Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Datasetcited by 434
  19. 2020Document Ranking with a Pretrained Sequence-to-Sequence Modelcited by 376
  20. 2019Explain Yourself! Leveraging Language Models for Commonsense Reasoningcited by 367
  21. 2014Memory Networkscited by 363
  22. 2021Beyond Goldfish Memory: Long-Term Open-Domain Conversationcited by 267
  23. 2022Can language models learn from explanations in context?cited by 249
  24. 2022Transformer Memory as a Differentiable Search Indexcited by 247
  25. 2021Efficiently Teaching an Effective Dense Retriever with Balanced Topic Aware Samplingcited by 238
  26. 2021SPoT: Better Frozen Model Adaptation through Soft Prompt Transfercited by 235
  27. 2018Explainable Recommendation: A Survey and New Perspectivescited by 210
  28. 2022BlenderBot 3: a deployed conversational agent that continually learns to responsibly engagecited by 198
  29. 2021GPT3Mix: Leveraging Large-scale Language Models for Text Augmentationcited by 187
  30. 2018Towards Deep Conversational Recommendationscited by 176
  31. 2020WT5?! Training Text-to-Text Models to Explain their Predictionscited by 148
  32. 2020A Survey on Conversational Recommender Systemscited by 143
  33. 2018Training Millions of Personalized Dialogue Agentscited by 126
  34. 2021Advances and Challenges in Conversational Recommender Systems: A Surveycited by 118
  35. 2018Conversational Recommender Systemcited by 115
  36. 2019Towards Knowledge-Based Recommender Dialog Systemcited by 113
  37. 2020Estimation-Action-Reflection: Towards Deep Interaction Between Conversational and Recommender Systemscited by 98
  38. 2019ConveRT: Efficient and Accurate Conversational Representations from Transformerscited by 95

50 most cited of 81 All 81 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 18; 2024: 32; 2025: 8; 2026: 5.

63 papers.

Sort:

By area:

  1. 2023A Survey on Large Language Models for Recommendationcited by 379
  2. 2023Recommender Systems in the Era of Large Language Models (LLMs)cited by 189
  3. 2024Retrieval-Augmented Generation with Graphs (GraphRAG)cited by 172
  4. 2023How Can Recommender Systems Benefit from Large Language Models: A Surveycited by 142
  5. 2023Large Language Models as Zero-Shot Conversational Recommenderscited by 127
  6. 2023When Large Language Models Meet Personalization: Perspectives of Challenges and Opportunitiescited by 90
  7. 2023ReLLa: Retrieval-enhanced Large Language Models for Lifelong Sequential Behavior Comprehension in Recommendationcited by 77
  8. 2023Large Language Models for Generative Recommendation: A Survey and Visionary Discussionscited by 73
  9. 2023Large Language Models are Competitive Near Cold-start Recommenders for Language- and Item-based Preferencescited by 66
  10. 2024Speak Out of Turn: Safety Vulnerability of Large Language Models in Multi-turn Dialoguecited by 66
  11. 2024HLLM: Enhancing Sequential Recommendations via Hierarchical Large Language Models for Item and User Modelingcited by 63
  12. 2024A Review of Modern Recommender Systems Using Generative Models (Gen-RecSys)cited by 58
38 more
  1. 2024Can Large Language Models be Good Emotional Supporter? Mitigating Preference Bias on Emotional Support Conversationcited by 55
  2. 2024ALI-Agent: Assessing LLMs' Alignment with Human Values via Agent-based Evaluationcited by 47
  3. 2023Knowledge-Augmented Large Language Models for Personalized Contextual Query Suggestioncited by 43
  4. 2024A Multi-Agent Conversational Recommender Systemcited by 43
  5. 2024Exploring Autonomous Agents through the Lens of Large Language Models: A Reviewcited by 31
  6. 2023RAH! RecSys-Assistant-Human: A Human-Centered Recommendation Framework with LLM Agentscited by 30
  7. 2024Leveraging LLM Reasoning Enhances Personalized Recommender Systemscited by 28
  8. 2024How Reliable is Your Simulator? Analysis on the Limitations of Current LLM-based User Simulators for Conversational Recommendationcited by 27
  9. 2024Towards Next-Generation LLM-based Recommender Systems: A Survey and Beyondcited by 26
  10. 2025Towards Agentic Recommender Systems in the Era of Multimodal Large Language Modelscited by 26
  11. 2024LLM-Enhanced User-Item Interactions: Leveraging Edge Information for Optimized Recommendationscited by 24
  12. 2025iAgent: LLM Agent as a Shield between User and Recommender Systemscited by 23
  13. 2025AgentRecBench: Benchmarking LLM Agent-based Personalized Recommender Systemscited by 23
  14. 2023ChoiceMates: Supporting Unfamiliar Online Decision-Making with Multi-Agent Conversational Interactionscited by 22
  15. 2024A Survey of Conversational Searchcited by 22
  16. 2023MuseChat: A Conversational Music Recommendation System for Videoscited by 21
  17. 2023User Modeling in the Era of Large Language Models: Current Research and Future Directionscited by 18
  18. 2024Bayesian Optimization with LLM-Based Acquisition Functions for Natural Language Preference Elicitationcited by 17
  19. 2023Conversational Recommender System and Large Language Model Are Made for Each Other in E-commerce Pre-sales Dialoguecited by 15
  20. 2023Recent Developments in Recommender Systems: A Surveycited by 14
  21. 2024Exploring the Impact of Large Language Models on Recommender Systems: An Extensive Reviewcited by 12
  22. 2024Behavior Alignment: A New Perspective of Evaluating LLM-based Conversational Recommender Systemscited by 11
  23. 2024Elaborative Subtopic Query Reformulation for Broad and Indirect Queries in Travel Destination Recommendationcited by 11
  24. 2024Reindex-Then-Adapt: Improving Large Language Models for Conversational Recommendationcited by 10
  25. 2025A Survey of Scaling in Large Language Model Reasoningcited by 10
  26. 2024Beyond the Safety Bundle: Auditing the Helpful and Harmless Datasetcited by 8
  27. 2023Modeling Recommender Ecosystems: Research Challenges at the Intersection of Mechanism Design, Reinforcement Learning and Generative Modelscited by 7
  28. 2024Unveiling Bias in Fairness Evaluations of Large Language Models: A Critical Literature Review of Music and Movie Recommendation Systemscited by 7
  29. 2024Molar: Multimodal LLMs with Collaborative Filtering Alignment for Enhanced Sequential Recommendationcited by 7
  30. 2025Towards Personalized Conversational Sales Agents: Contextual User Profiling for Strategic Actioncited by 6
  31. 2024Frontier AI Ethics: Anticipating and Evaluating the Societal Impacts of Language Model Agentscited by 5
  32. 2024Enhancing Collaborative Semantics of Language Model-Driven Recommendations via Graph-Aware Learningcited by 5
  33. 2024Evaluating Search Engines and Large Language Models for Answering Health Questionscited by 5
  34. 2023Factual and Personalized Recommendations using Language Models and Reinforcement Learningcited by 4
  35. 2023Modeling User Viewing Flow Using Large Language Models for Article Recommendationcited by 4
  36. 2024Reasoning over User Preferences: Knowledge Graph-Augmented LLMs for Explainable Conversational Recommendationscited by 4
  37. 2025CTRL-Rec: Controlling Recommender Systems With Natural Languagecited by 4
  38. 2024Engineering Conversational Search Systems: A Review of Applications, Architectures, and Functional Componentscited by 3

50 most cited of 63 All 63 (JSON)