mlsanityData to 13 Oct 2026

Large Language Models are Competitive Near Cold-start Recommenders for Language- and Item-based Preferences

arXiv 2307.14225 ↗First posted 26 Jul 2023cs.IR cs.LGcited by 66

Not on the map. Why?

Abstract (arXiv)

Traditional recommender systems leverage users' item preference history to recommend novel content that users may like. However, modern dialog interfaces that allow users to express language-based preferences offer a fundamentally different modality for preference input. Inspired by recent successes of prompting paradigms for large language models (LLMs), we study their use for making recommendations from both item-based and language-based preferences in comparison to state-of-the-art item-based collaborative filtering (CF) methods. To support this investigation, we collect a new dataset consisting of both item-based and language-based preferences elicited from users along with their ratings on a variety of (biased) recommended items and (unbiased) random items. Among numerous experimental results, we find that LLMs provide competitive recommendation performance for pure language-based preferences (no item preferences) in the near cold-start case in comparison to item-based CF methods, despite having no supervised training for this specific task (zero-shot) or only a few labels (few-shot). This is particularly promising as language-based preference representations are more explainable and scrutable than item-based or vector-based representations.

Key facts. Cited by 66 papers in the map (data through 13 Oct 2026). Builds on 26 of its 47 references that are in the map. First posted on arXiv 26 Jul 2023.

Builds on

26 of 47 references.

References · 26

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,304
  2. 2020Language Models are Few-Shot Learnerscited by 32,320
  3. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,317
  4. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,765
  5. 2021Program Synthesis with Large Language Modelscited by 3,573
  6. 2017Neural Collaborative Filteringcited by 1,110
  7. 2022Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5)cited by 397
  8. 2018Variational Autoencoders for Collaborative Filteringcited by 309
  9. 2023Large Language Models are Zero-Shot Rankers for Recommender Systemscited by 308
  10. 2022Language Models are Realistic Tabular Data Generatorscited by 292
  11. 2019Are We Really Making Much Progress? A Worrying Analysis of Recent Neural Recommendation Approachescited by 182
  12. 2020A Survey on Conversational Recommender Systemscited by 143
14 more
  1. 2022Towards Universal Sequence Representation Learning for Recommender Systemscited by 120
  2. 2021Advances and Challenges in Conversational Recommender Systems: A Surveycited by 118
  3. 2023Do LLMs Understand User Preferences? Evaluating LLMs On User Rating Predictioncited by 114
  4. 2019Embarrassingly Shallow Autoencoders for Sparse Datacited by 93
  5. 2023Leveraging Large Language Models in Conversational Recommender Systemscited by 63
  6. 2020What does BERT know about books, movies and music? Probing BERT for Conversational Recommendationcited by 36
  7. 2023Large Language Model Augmented Narrative Driven Recommendationscited by 31
  8. 2022On Natural Language User Profiles for Transparent and Scrutable Recommendationcited by 23
  9. 2022Denoising Self-attentive Sequential Recommendationcited by 20
  10. 2021On Interpretation and Measurement of Soft Attributes for Recommendationcited by 19
  11. 2023Editable User Profiles for Controllable Text Recommendationcited by 16
  12. 2021DOCENT: Learning Self-Supervised Entity Representations from Large Document Collectionscited by 13
  13. 2020RecoBERT: A Catalog Language Model for Text-Based Recommendationscited by 8
  14. 2023Beyond Single Items: Exploring User Preferences in Item Sets with the Conversational Playlist Curation Datasetcited by 7

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2023: 7; 2024: 28; 2025: 25; 2026: 6.

66 papers.

Sort:

By area:

  1. 2024A Review of Modern Recommender Systems Using Generative Models (Gen-RecSys)cited by 58
  2. 2024Large Language Models meet Collaborative Filtering: An Efficient All-round LLM-based Recommender Systemcited by 50
  3. 2024CoRAL: Collaborative Retrieval-Augmented Large Language Models Improve Long-tail Recommendationcited by 44
  4. 2023RAH! RecSys-Assistant-Human: A Human-Centered Recommendation Framework with LLM Agentscited by 30
  5. 2023Large Language Models for Intent-Driven Session Recommendationscited by 30
  6. 2024Towards Next-Generation LLM-based Recommender Systems: A Survey and Beyondcited by 26
  7. 2024LLM-Enhanced User-Item Interactions: Leveraging Edge Information for Optimized Recommendationscited by 24
  8. 2023Interactive AI Alignment: Specification, Process, and Evaluation Alignmentcited by 22
  9. 2024RDRec: Rationale Distillation for LLM-based Recommendationcited by 22
  10. 2024LEARN: Knowledge Adaptation from Large Language Model to Recommendation for Practical Industrial Applicationcited by 21
  11. 2023Evaluating ChatGPT as a Recommender System: A Rigorous Approachcited by 20
  12. 2023User Modeling in the Era of Large Language Models: Current Research and Future Directionscited by 18
38 more
  1. 2024Language-Based User Profiles for Recommendationcited by 18
  2. 2024Unifying Generative and Dense Retrieval for Sequential Recommendationcited by 16
  3. 2024LLMs with Industrial Lens: Deciphering the Challenges and Prospects -- A Surveycited by 12
  4. 2024A Multimodal Single-Branch Embedding Network for Recommendation in Cold-Start and Missing Modality Scenarioscited by 12
  5. 2025Uncertainty Quantification and Decomposition for LLM-based Recommendationcited by 12
  6. 2024Reindex-Then-Adapt: Improving Large Language Models for Conversational Recommendationcited by 10
  7. 2024End-to-end Training for Recommendation with Language-based User Profilescited by 10
  8. 2023Adaptive In-Context Learning with Large Language Models for Bundle Generationcited by 8
  9. 2024Incorporating External Knowledge and Goal Guidance for LLM-based Conversational Recommender Systemscited by 8
  10. 2024Enhancing High-order Interaction Awareness in LLM-based Recommender Modelcited by 8
  11. 2025Lost in Sequence: Do Large Language Models Understand Sequential Recommendation?cited by 8
  12. 2024RA-Rec: An Efficient ID Representation Alignment Framework for LLM-based Recommendationcited by 7
  13. 2025Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Modelscited by 7
  14. 2023Leveraging Large Language Models for Collective Decision-Makingcited by 6
  15. 2024ChatGPT for Conversational Recommendation: Refining Recommendations by Reprompting with Feedbackcited by 6
  16. 2024Preference Discerning with LLM-Enhanced Generative Retrievalcited by 6
  17. 2025Privacy Risks of LLM-Empowered Recommender Systems: An Inversion Attack Perspectivecited by 6
  18. 2025Revealing Potential Biases in LLM-Based Recommender Systems in the Cold Start Settingcited by 6
  19. 2024TEARS: Textual Representations for Scrutable Recommendationscited by 5
  20. 2025Magical: Medical Lay Language Generation via Semantic Invariance and Layperson-tailored Adaptationcited by 5
  21. 2025iNews: A Multimodal Dataset for Modeling Personalized Affective Responses to Newscited by 4
  22. 2025CTRL-Rec: Controlling Recommender Systems With Natural Languagecited by 4
  23. 2024Keyword-driven Retrieval-Augmented Large Language Models for Cold-start User Recommendationscited by 3
  24. 2024No Size Fits All: The Perils and Pitfalls of Leveraging LLMs Vary with Company Sizecited by 3
  25. 2024Break the ID-Language Barrier: An Adaption Framework for LLM-based Sequential Recommendationcited by 3
  26. 2025Adaptive political surveys and GPT-4: Tackling the cold start problem with simulated user interactionscited by 3
  27. 2025The Pitfalls of Growing Group Complexity: LLMs and Social Choice-Based Aggregation for Group Recommendationscited by 3
  28. 2024All-in-One: Heterogeneous Interaction Modeling for Cold-Start Rating Predictioncited by 2
  29. 2024Optimizing Novelty of Top-k Recommendations using Large Language Models and Reinforcement Learningcited by 2
  30. 2025Efficient and Responsible Adaptation of Large Language Models for Robust and Equitable Top-k Recommendationscited by 2
  31. 2025ACAI for SBOs: AI Co-creation for Advertising and Inspiration for Small Business Ownerscited by 2
  32. 2025Consistent Explainers or Unreliable Narrators? Understanding LLM-generated Group Recommendationscited by 2
  33. 2024Large Language Models as Conversational Movie Recommenders: A User Studycited by 1
  34. 2024Large Language Models as Narrative-Driven Recommenderscited by 1
  35. 2025What's in a Query: Polarity-Aware Distribution-Based Fair Rankingcited by 1
  36. 2025Do LLMs Understand Collaborative Signals? Diagnosis and Repaircited by 1
  37. 2025Enhancing Rating Prediction with Off-the-Shelf LLMs Using In-Context User Reviewscited by 1
  38. 2025Enhance Large Language Models as Recommendation Systems with Collaborative Filteringcited by 1

50 most cited of 66 All 66 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025A Comprehensive Review on Harnessing Large Language Models to Overcome Recommender System Challenges
  2. 2024Exploring the Impact of Large Language Models on Recommender Systems: An Extensive Review
  3. 2023How Can Recommender Systems Benefit from Large Language Models: A Survey
  4. 2025Bridging Collaborative Filtering and Large Language Models with Dynamic Alignment, Multimodal Fusion and Evidence-grounded Explanations
  5. 2024Aligning Large Language Models with Recommendation Knowledge
  6. 2023Empowering Few-Shot Recommender Systems with Large Language Models -- Enhanced Representations
  7. 2024All Roads Lead to Rome: Unveiling the Trajectory of Recommender Systems Across the LLM Era
  8. 2024Bayesian Optimization with LLM-Based Acquisition Functions for Natural Language Preference Elicitation