mlsanityData to 14 Oct 2026

ReGeS: Reciprocal Retrieval-Generation Synergy for Conversational Recommender Systems

arXiv 2509.21371 ↗First posted 22 Sep 2025cs.IR cs.AI cs.CLcited by 2

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

Abstract (arXiv)

Connecting conversation with external domain knowledge is vital for conversational recommender systems (CRS) to correctly understand user preferences. However, existing solutions either require domain-specific engineering, which limits flexibility, or rely solely on large language models, which increases the risk of hallucination. While Retrieval-Augmented Generation (RAG) holds promise, its naive use in CRS is hindered by noisy dialogues that weaken retrieval and by overlooked nuances among similar items. We propose ReGeS, a reciprocal Retrieval-Generation Synergy framework that unifies generation-augmented retrieval to distill informative user intent from conversations and retrieval-augmented generation to differentiate subtle item features. This synergy obviates the need for extra annotations, reduces hallucinations, and simplifies continuous updates. Experiments on multiple CRS benchmarks show that ReGeS achieves state-of-the-art performance in recommendation accuracy, demonstrating the effectiveness of reciprocal synergy for knowledge-intensive CRS tasks.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in RAG for recommendation, one of 15 directions in Retrieval-augmented generation. Builds on 21 of its 37 references that are in the map. First posted on arXiv 22 Sep 2025.

Builds on

21 of 37 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024RAMO: Retrieval-Augmented Generation for Enhancing MOOCs Recommendations6 Jul

Other references · 20

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  3. 2022Text Embeddings by Weakly-Supervised Contrastive Pre-trainingcited by 1,253
  4. 2021Retrieval Augmentation Reduces Hallucination in Conversationcited by 692
  5. 2023A Survey on Large Language Models for Recommendationcited by 379
  6. 2018Towards Deep Conversational Recommendationscited by 176
  7. 2020Improving Conversational Recommender Systems via Knowledge Graph based Semantic Fusioncited by 122
  8. 2021Advances and Challenges in Conversational Recommender Systems: A Surveycited by 118
  9. 2019Towards Knowledge-Based Recommender Dialog Systemcited by 113
  10. 2020INSPIRED: Toward Sociable Recommendation Dialog Systemscited by 93
  11. 2022Towards Unified Conversational Recommender Systems via Knowledge-Enhanced Prompt Learningcited by 86
  12. 2024Retrieval-Augmented Generation for Natural Language Processing: A Surveycited by 71
8 more
  1. 2024LLM4Rerank: LLM-based Auto-Reranking Framework for Recommendationscited by 40
  2. 2021CRSLab: An Open-Source Toolkit for Building Conversational Recommender Systemcited by 34
  3. 2023A Large Language Model Enhanced Conversational Recommender Systemcited by 31
  4. 2024Do Large Language Models Rank Fairly? An Empirical Study on the Fairness of LLMs as Rankerscited by 17
  5. 2024Behavior Alignment: A New Perspective of Evaluating LLM-based Conversational Recommender Systemscited by 11
  6. 2024On the Benchmarking of LLMs for Open-Domain Dialogue Evaluationcited by 10
  7. 2023ZeQR: Zero-shot Query Reformulation for Conversational Searchcited by 4
  8. 2024Simple but Efficient: A Multi-Scenario Nearline Retrieval Framework for Recommendation on Taobaocited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Where and What: Reasoning Dynamic and Implicit Preferences in Situated Conversational Recommendationcited by 1
  2. 2026Re2A: Situated Conversational Recommendation via Rubric-based Preference Reasoning and Alignmentcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Retrieval Augmented Conversational Recommendation with Reinforcement Learning
  2. 2024Beyond Retrieval: Generating Narratives in Conversational Recommender Systems
  3. 2025Evaluating Conversational Recommender Systems via Large Language Models: A User-Centric Framework
  4. 2025Graph Retrieval-Augmented LLM for Conversational Recommendation Systems
  5. 2025Collaborative Retrieval for Large Language Model-based Conversational Recommender Systems
  6. 2025Enhancing Conversational Recommender Systems with Tree-Structured Knowledge and Pretrained Language Models
  7. 2023Rethinking the Evaluation for Conversational Recommendation in the Era of Large Language Models
  8. 2025A Comprehensive Review on Harnessing Large Language Models to Overcome Recommender System Challenges