mlsanityData to 7 Oct 2026

Retrieval-Augmented Conversational Recommendation with Prompt-based Semi-Structured Natural Language State Tracking

arXiv 2406.00033 ↗First posted 25 May 2024cs.CL cs.AIcited by 18

On the map: Retrieval-augmented generation → RAG for recommendation

Abstract (arXiv)

Conversational recommendation (ConvRec) systems must understand rich and diverse natural language (NL) expressions of user preferences and intents, often communicated in an indirect manner (e.g., "I'm watching my weight"). Such complex utterances make retrieving relevant items challenging, especially if only using often incomplete or out-of-date metadata. Fortunately, many domains feature rich item reviews that cover standard metadata categories and offer complex opinions that might match a user's interests (e.g., "classy joint for a date"). However, only recently have large language models (LLMs) let us unlock the commonsense connections between user preference utterances and complex language in user-generated reviews. Further, LLMs enable novel paradigms for semi-structured dialogue state tracking, complex intent and preference understanding, and generating recommendations, explanations, and question answers. We thus introduce a novel technology RA-Rec, a Retrieval-Augmented, LLM-driven dialogue state tracking system for ConvRec, showcased with a video, open source GitHub repository, and interactive Google Colab notebook.

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). Placed in RAG for recommendation, one of 15 directions in Retrieval-augmented generation. Builds on 13 of its 29 references that are in the map. First posted on arXiv 25 May 2024.

Builds on

13 of 29 references.

References · 13

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  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. 2021Efficiently Teaching an Effective Dense Retriever with Balanced Topic Aware Samplingcited by 238
  5. 2020A Survey on Conversational Recommender Systemscited by 142
  6. 2018Conversational Recommender Systemcited by 115
  7. 2024A Review of Modern Recommender Systems Using Generative Models (Gen-RecSys)cited by 58
  8. 2020"I'd rather just go to bed": Understanding Indirect Answerscited by 36
  9. 2024Bayesian Optimization with LLM-Based Acquisition Functions for Natural Language Preference Elicitationcited by 17
  10. 2013Conversation as Action Under Uncertaintycited by 11
  11. 2023Self-Supervised Contrastive BERT Fine-tuning for Fusion-based Reviewed-Item Retrievalcited by 6
  12. 2017Design Patterns for Fusion-Based Object Retrievalcited by 3
1 more
  1. 2022Resolving Indirect Referring Expressions for Entity Selectioncited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 6; 2026: 10.

18 papers.

Sort:

By area:

  1. 2024Elaborative Subtopic Query Reformulation for Broad and Indirect Queries in Travel Destination Recommendationcited by 11
  2. 2025Retrieval-Augmented Purifier for Robust LLM-Empowered Recommendationcited by 7
  3. 2026Autonomous Information Seeking: A Roadmap for Agentic Recommender Systemscited by 3
  4. 2025WebRec: Enhancing LLM-based Recommendations with Attention-guided RAG from Webcited by 2
  5. 2026Retrieval Augmented Conversational Recommendation with Reinforcement Learningcited by 2
  6. 2025Multi-Type Context-Aware Conversational Recommender Systems via Mixture-of-Expertscited by 1
  7. 2025Augment or Not? A Comparative Study of Pure and Augmented Large Language Model Recommenderscited by 1
  8. 2025Catalog-Native LLM: Speaking Item-ID Dialect with Less Entanglement for Recommendationcited by 1
  9. 2026U-CAN: Utility-Aware Contrastive Attenuation for Efficient Unlearning in Generative Recommendationcited by 1
  10. 2026TRACE: A Conversational Framework for Sustainable Tourism Recommendation with Agentic Counterfactual Explanationscited by 1
  11. 2026TRACE: Tourism Recommendation with Accountable Citation Evidencecited by 1
  12. 2024Large Language Model Driven Recommendationcited by 0
6 more
  1. 2025LatentCRS: A Variational EM Framework for Bridging Semantics and Behavior in LLM-based Conversational Recommendationcited by 0
  2. 2026Beyond Factual Correctness: Mitigating Preference-Inconsistent Explanations in Explainable Recommendationcited by 0
  3. 2026NBQ: Next-Best-Question for Dynamic Profilingcited by 0
  4. 2026Two Views, One Voice: Evidence-Grounded Conversational Music Recommendationcited by 0
  5. 2026Shape Your Feed: An LLM-based Agentic System for Conversational Recommendationcited by 0
  6. 2026Towards Effective Structured Context Modeling for Conversational Recommender Systems via Dual-node Monte Carlo Tree Searchcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Graph Retrieval-Augmented LLM for Conversational Recommendation Systems
  2. 2025A Framework for Generating Conversational Recommendation Datasets from Behavioral Interactions
  3. 2025ReGeS: Reciprocal Retrieval-Generation Synergy for Conversational Recommender Systems
  4. 2025A Comprehensive Review on Harnessing Large Language Models to Overcome Recommender System Challenges
  5. 2025RALLRec+: Retrieval Augmented Large Language Model Recommendation with Reasoning
  6. 2023Rethinking the Evaluation for Conversational Recommendation in the Era of Large Language Models
  7. 2025RALLRec: Improving Retrieval Augmented Large Language Model Recommendation with Representation Learning
  8. 2023A Large Language Model Enhanced Conversational Recommender System