mlsanityData to 7 Oct 2026

Beyond Retrieval: Generating Narratives in Conversational Recommender Systems

arXiv 2410.16780 ↗First posted 22 Oct 2024cs.CL cs.AI cs.IRcited by 8

On the map: LLM reasoning → LLM reasoning for recommendation

Abstract (arXiv)

The recent advances in Large Language Model's generation and reasoning capabilities present an opportunity to develop truly conversational recommendation systems. However, effectively integrating recommender system knowledge into LLMs for natural language generation which is tailored towards recommendation tasks remains a challenge. This paper addresses this challenge by making two key contributions. First, we introduce a new dataset (REGEN) for natural language generation tasks in conversational recommendations. REGEN (Reviews Enhanced with GEnerative Narratives) extends the Amazon Product Reviews dataset with rich user narratives, including personalized explanations of product preferences, product endorsements for recommended items, and summaries of user purchase history. REGEN is made publicly available to facilitate further research. Furthermore, we establish benchmarks using well-known generative metrics, and perform an automated evaluation of the new dataset using a rater LLM. Second, the paper introduces a fusion architecture (CF model with an LLM) which serves as a baseline for REGEN. And to the best of our knowledge, represents the first attempt to analyze the capabilities of LLMs in understanding recommender signals and generating rich narratives. We demonstrate that LLMs can effectively learn from simple fusion architectures utilizing interaction-based CF embeddings, and this can be further enhanced using the metadata and personalization data associated with items. Our experiments show that combining CF and content embeddings leads to improvements of 4-12% in key language metrics compared to using either type of embedding individually. We also provide an analysis to interpret how CF and content embeddings contribute to this new generative task.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Placed in LLM reasoning for recommendation, one of 17 directions in LLM reasoning. Builds on 32 of its 55 references that are in the map. First posted on arXiv 22 Oct 2024.

Builds on

32 of 55 references.

References · 32

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  3. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  4. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,878
  5. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,769
  6. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,175
  7. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,168
  8. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  9. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,722
  10. 2021Improving language models by retrieving from trillions of tokenscited by 1,278
  11. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,203
  12. 2019BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformercited by 952
20 more
  1. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 940
  2. 2023Can Large Language Models Be an Alternative to Human Evaluations?cited by 729
  3. 2018Universal Sentence Encodercited by 485
  4. 2021Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Modelscited by 462
  5. 2017Supervised Learning of Universal Sentence Representations from Natural Language Inference Datacited by 428
  6. 2020S^3-Rec: Self-Supervised Learning for Sequential Recommendation with Mutual Information Maximizationcited by 311
  7. 2024Bridging Language and Items for Retrieval and Recommendation: Benchmarking LLMs as Semantic Encoderscited by 213
  8. 2020A Survey on Conversational Recommender Systemscited by 142
  9. 2020Neural Collaborative Filtering vs. Matrix Factorization Revisitedcited by 123
  10. 2024User-LLM: Efficient LLM Contextualization with User Embeddingscited by 74
  11. 2024Foundational Autoraters: Taming Large Language Models for Better Automatic Evaluationcited by 72
  12. 2023Better Generalization with Semantic IDs: A Case Study in Ranking for Recommendationscited by 50
  13. 2024Large Language Models meet Collaborative Filtering: An Efficient All-round LLM-based Recommender Systemcited by 50
  14. 2023Bridging Items and Language: A Transition Paradigm for Large Language Model-Based Recommendationcited by 29
  15. 2024User Embedding Model for Personalized Language Promptingcited by 28
  16. 2024PERSOMA: PERsonalized SOft ProMpt Adapter Architecture for Personalized Language Promptingcited by 13
  17. 2024EB-NeRD: A Large-Scale Dataset for News Recommendationcited by 12
  18. 2024Item-Language Model for Conversational Recommendationcited by 7
  19. 2024Unlocking the `Why' of Buying: Introducing a New Dataset and Benchmark for Purchase Reason and Post-Purchase Experiencecited by 4
  20. 2024FLARE: Fusing Language Models and Collaborative Architectures for Recommender Enhancementcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 5; 2026: 3.

8 papers.

  1. 2025A Survey of Personalized Large Language Models: Progress and Future Directionscited by 65
  2. 2025A Survey on Personalized Alignment -- The Missing Piece for Large Language Models in Real-World Applicationscited by 40
  3. 2025Towards Personalized Conversational Sales Agents: Contextual User Profiling for Strategic Actioncited by 6
  4. 2026Autonomous Information Seeking: A Roadmap for Agentic Recommender Systemscited by 3
  5. 2025Music Recommendation with Large Language Models: Challenges, Opportunities, and Evaluationcited by 1
  6. 2025YNTP-100: A Benchmark for Your Next Token Prediction with 100 Peoplecited by 0
  7. 2026The Subjectivity of Respect in Police Traffic Stops: Modeling Community Perspectives in Body-Worn Camera Footagecited by 0
  8. 2026VIBE-Bench: Evaluating Personalized Large Language Models When Profiles Don't Mean Preferencescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Large Language Model Driven Recommendation
  2. 2025A Comprehensive Review on Harnessing Large Language Models to Overcome Recommender System Challenges
  3. 2023Empowering Few-Shot Recommender Systems with Large Language Models -- Enhanced Representations
  4. 2025ReGeS: Reciprocal Retrieval-Generation Synergy for Conversational Recommender Systems
  5. 2024Aligning Large Language Models with Recommendation Knowledge
  6. 2025Graph Retrieval-Augmented LLM for Conversational Recommendation Systems
  7. 2025Evaluating Conversational Recommender Systems via Large Language Models: A User-Centric Framework
  8. 2022Evaluation of Synthetic Datasets for Conversational Recommender Systems