mlsanityData to 7 Oct 2026

Advances and Challenges in Conversational Recommender Systems: A Survey

arXiv 2101.09459 ↗First posted 23 Jan 2021cs.IR cs.CLcited by 118

Not on the map. Why?

Abstract (arXiv)

Recommender systems exploit interaction history to estimate user preference, having been heavily used in a wide range of industry applications. However, static recommendation models are difficult to answer two important questions well due to inherent shortcomings: (a) What exactly does a user like? (b) Why does a user like an item? The shortcomings are due to the way that static models learn user preference, i.e., without explicit instructions and active feedback from users. The recent rise of conversational recommender systems (CRSs) changes this situation fundamentally. In a CRS, users and the system can dynamically communicate through natural language interactions, which provide unprecedented opportunities to explicitly obtain the exact preference of users. Considerable efforts, spread across disparate settings and applications, have been put into developing CRSs. Existing models, technologies, and evaluation methods for CRSs are far from mature. In this paper, we provide a systematic review of the techniques used in current CRSs. We summarize the key challenges of developing CRSs in five directions: (1) Question-based user preference elicitation. (2) Multi-turn conversational recommendation strategies. (3) Dialogue understanding and generation. (4) Exploitation-exploration trade-offs. (5) Evaluation and user simulation. These research directions involve multiple research fields like information retrieval (IR), natural language processing (NLP), and human-computer interaction (HCI). Based on these research directions, we discuss some future challenges and opportunities. We provide a road map for researchers from multiple communities to get started in this area. We hope this survey can help to identify and address challenges in CRSs and inspire future research.

Key facts. Cited by 118 papers in the map (data through 7 Oct 2026). Builds on 130 of its 292 references that are in the map. First posted on arXiv 23 Jan 2021.

Builds on

130 of 292 references.

References · 130

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  3. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  4. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  5. 2013Playing Atari with Deep Reinforcement Learningcited by 3,211
  6. 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
  7. 2015Trust Region Policy Optimizationcited by 2,503
  8. 2020Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problemscited by 1,873
  9. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,684
  10. 2019Simplifying Graph Convolutional Networkscited by 1,470
  11. 2020LightGCN: Simplifying and Powering Graph Convolution Network for Recommendationcited by 1,134
  12. 2018Graph Convolutional Neural Networks for Web-Scale Recommender Systemscited by 1,133
38 more
  1. 2014Convolutional Neural Networks for Sentence Classificationcited by 1,124
  2. 2017Neural Collaborative Filteringcited by 1,108
  3. 2018Deep Graph Infomaxcited by 1,101
  4. 2015A Diversity-Promoting Objective Function for Neural Conversation Modelscited by 1,068
  5. 2016ConceptNet 5.5: An Open Multilingual Graph of General Knowledgecited by 1,065
  6. 2018MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modellingcited by 760
  7. 2016Wide & Deep Learning for Recommender Systemscited by 745
  8. 2015Image-based Recommendations on Styles and Substitutescited by 702
  9. 2017Deep Interest Network for Click-Through Rate Predictioncited by 541
  10. 2020Graph Neural Networks in Recommender Systems: A Surveycited by 493
  11. 2016RL2: Fast Reinforcement Learning via Slow Reinforcement Learningcited by 490
  12. 2016Learning to reinforcement learncited by 369
  13. 2016How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generationcited by 356
  14. 2016Deep Reinforcement Learning for Dialogue Generationcited by 286
  15. 2020Evaluation of Text Generation: A Surveycited by 275
  16. 2020Bias and Debias in Recommender System: A Survey and Future Directionscited by 239
  17. 2017Why We Need New Evaluation Metrics for NLGcited by 232
  18. 2016Key-Value Memory Networks for Directly Reading Documentscited by 223
  19. 2018Explainable Recommendation: A Survey and New Perspectivescited by 210
  20. 2019Persuasion for Good: Towards a Personalized Persuasive Dialogue System for Social Goodcited by 207
  21. 2017Deal or No Deal? End-to-End Learning for Negotiation Dialoguescited by 202
  22. 2021Reinforcement learning based recommender systems: A surveycited by 187
  23. 2017Learning to Ask: Neural Question Generation for Reading Comprehensioncited by 186
  24. 2017Neural Factorization Machines for Sparse Predictive Analyticscited by 183
  25. 2018Top-K Off-Policy Correction for a REINFORCE Recommender Systemcited by 181
  26. 2021Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answeringcited by 178
  27. 2018Towards Deep Conversational Recommendationscited by 174
  28. 2020A Survey on Knowledge Graph-Based Recommender Systemscited by 170
  29. 2017Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memorycited by 167
  30. 2017A Survey on Dialogue Systems: Recent Advances and New Frontierscited by 162
  31. 2020A Survey on Conversational Recommender Systemscited by 142
  32. 2017Deep Learning based Recommender System: A Survey and New Perspectivescited by 136
  33. 2018Ranking Sentences for Extractive Summarization with Reinforcement Learningcited by 128
  34. 2019Survey on Evaluation Methods for Dialogue Systemscited by 126
  35. 2020Improving Conversational Recommender Systems via Knowledge Graph based Semantic Fusioncited by 122
  36. 2019MeLU: Meta-Learned User Preference Estimator for Cold-Start Recommendationcited by 119
  37. 2020Disentangled Graph Collaborative Filteringcited by 118
  38. 2015Ask Me Anything: Dynamic Memory Networks for Natural Language Processingcited by 116

50 most cited of 130 All 130 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 10; 2022: 17; 2023: 29; 2024: 19; 2025: 29; 2026: 14.

118 papers.

Sort:

By area:

  1. 2023Recommendation as Instruction Following: A Large Language Model Empowered Recommendation Approachcited by 168
  2. 2023Recommender AI Agent: Integrating Large Language Models for Interactive Recommendationscited by 130
  3. 2021Learning Intents behind Interactions with Knowledge Graph for Recommendationcited by 94
  4. 2022GCNet: Graph Completion Network for Incomplete Multimodal Learning in Conversationcited by 86
  5. 2022Towards Unified Conversational Recommender Systems via Knowledge-Enhanced Prompt Learningcited by 85
  6. 2023Plug-and-Play Policy Planner for Large Language Model Powered Dialogue Agentscited by 76
  7. 2023Large Language Models are Competitive Near Cold-start Recommenders for Language- and Item-based Preferencescited by 66
  8. 2023Leveraging Large Language Models in Conversational Recommender Systemscited by 63
  9. 2023Rethinking the Evaluation for Conversational Recommendation in the Era of Large Language Modelscited by 48
  10. 2024Evaluating Large Language Models as Generative User Simulators for Conversational Recommendationcited by 45
  11. 2022A Unified Multi-task Learning Framework for Multi-goal Conversational Recommender Systemscited by 32
  12. 2023A Large Language Model Enhanced Conversational Recommender Systemcited by 31
38 more
  1. 2024How Reliable is Your Simulator? Analysis on the Limitations of Current LLM-based User Simulators for Conversational Recommendationcited by 25
  2. 2024Large Language Models are Learnable Planners for Long-Term Recommendationcited by 24
  3. 2025iAgent: LLM Agent as a Shield between User and Recommender Systemscited by 23
  4. 2022Variational Reasoning over Incomplete Knowledge Graphs for Conversational Recommendationcited by 22
  5. 2023ChoiceMates: Supporting Unfamiliar Online Decision-Making with Multi-Agent Conversational Interactionscited by 22
  6. 2024A Survey of Conversational Searchcited by 22
  7. 2023MuseChat: A Conversational Music Recommendation System for Videoscited by 21
  8. 2025A Survey of Foundation Model-Powered Recommender Systems: From Feature-Based, Generative to Agentic Paradigmscited by 17
  9. 2023Conversational Recommender System and Large Language Model Are Made for Each Other in E-commerce Pre-sales Dialoguecited by 15
  10. 2021KECRS: Towards Knowledge-Enriched Conversational Recommendation Systemcited by 14
  11. 2022Empathetic Conversational Systems: A Review of Current Advances, Gaps, and Opportunitiescited by 14
  12. 2023A Survey on Fairness-aware Recommender Systemscited by 14
  13. 2025The Future is Agentic: Definitions, Perspectives, and Open Challenges of Multi-Agent Recommender Systemscited by 14
  14. 2023Sparks of Artificial General Recommender (AGR): Early Experiments with ChatGPTcited by 13
  15. 2022Comparison-based Conversational Recommender System with Relative Bandit Feedbackcited by 12
  16. 2023Efficient Explorative Key-term Selection Strategies for Conversational Contextual Banditscited by 12
  17. 2023U-NEED: A Fine-grained Dataset for User Needs-Centric E-commerce Conversational Recommendationcited by 12
  18. 2024A LLM-based Controllable, Scalable, Human-Involved User Simulator Framework for Conversational Recommender Systemscited by 12
  19. 2021Wizard of Search Engine: Access to Information Through Conversations with Search Enginescited by 11
  20. 2023Improving Conversational Recommendation Systems via Bias Analysis and Language-Model-Enhanced Data Augmentationcited by 11
  21. 2024Behavior Alignment: A New Perspective of Evaluating LLM-based Conversational Recommender Systemscited by 11
  22. 2025RecUserSim: A Realistic and Diverse User Simulator for Evaluating Conversational Recommender Systemscited by 11
  23. 2025Pluralistic Off-policy Evaluation and Alignmentcited by 11
  24. 2021Generating Usage-related Questions for Preference Elicitation in Conversational Recommender Systemscited by 10
  25. 2022Reinforcement Learning and Bandits for Speech and Language Processing: Tutorial, Review and Outlookcited by 10
  26. 2023Improving Conversational Recommendation Systems via Counterfactual Data Simulationcited by 10
  27. 2022Metaphorical User Simulators for Evaluating Task-oriented Dialogue Systemscited by 9
  28. 2023Talk the Walk: Synthetic Data Generation for Conversational Music Recommendationcited by 9
  29. 2024Parameter-Efficient Conversational Recommender System as a Language Processing Taskcited by 9
  30. 2024Concept -- An Evaluation Protocol on Conversational Recommender Systems with System-centric and User-centric Factorscited by 9
  31. 2024Towards Empathetic Conversational Recommender Systemscited by 9
  32. 2024Incorporating External Knowledge and Goal Guidance for LLM-based Conversational Recommender Systemscited by 8
  33. 2025MemWeaver: A Hierarchical Memory from Textual Interactive Behaviors for Personalized Generationcited by 8
  34. 2024Beyond Persuasion: Towards Conversational Recommender System with Credible Explanationscited by 7
  35. 2021Towards Standard Criteria for human evaluation of Chatbots: A Surveycited by 6
  36. 2022Aligning Recommendation and Conversation via Dual Imitationcited by 6
  37. 2023Lending Interaction Wings to Recommender Systems with Conversational Agentscited by 6
  38. 2024FedConPE: Efficient Federated Conversational Bandits with Heterogeneous Clientscited by 6

50 most cited of 118 All 118 (JSON)