# ReGeS: Reciprocal Retrieval-Generation Synergy for Conversational Recommender Systems

arXiv: https://arxiv.org/abs/2509.21371 · HTML: https://mlsanity.com/paper/2509.21371/

## 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.

## Placed in

- Retrieval-augmented generation / [RAG for recommendation](https://mlsanity.com/rag/rag-for-recommendation/)

## Builds on (most cited first, 21 of 21)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Text Embeddings by Weakly-Supervised Contrastive Pre-training](https://mlsanity.com/paper/2212.03533/) (2022)
- [Retrieval Augmentation Reduces Hallucination in Conversation](https://mlsanity.com/paper/2104.07567/) (2021)
- [A Survey on Large Language Models for Recommendation](https://mlsanity.com/paper/2305.19860/) (2023)
- [Towards Deep Conversational Recommendations](https://mlsanity.com/paper/1812.07617/) (2018)
- [Improving Conversational Recommender Systems via Knowledge Graph based Semantic Fusion](https://mlsanity.com/paper/2007.04032/) (2020)
- [Advances and Challenges in Conversational Recommender Systems: A Survey](https://mlsanity.com/paper/2101.09459/) (2021)
- [Towards Knowledge-Based Recommender Dialog System](https://mlsanity.com/paper/1908.05391/) (2019)
- [INSPIRED: Toward Sociable Recommendation Dialog Systems](https://mlsanity.com/paper/2009.14306/) (2020)
- [Towards Unified Conversational Recommender Systems via Knowledge-Enhanced Prompt Learning](https://mlsanity.com/paper/2206.09363/) (2022)
- [Retrieval-Augmented Generation for Natural Language Processing: A Survey](https://mlsanity.com/paper/2407.13193/) (2024)
- [LLM4Rerank: LLM-based Auto-Reranking Framework for Recommendations](https://mlsanity.com/paper/2406.12433/) (2024)
- [CRSLab: An Open-Source Toolkit for Building Conversational Recommender System](https://mlsanity.com/paper/2101.00939/) (2021)
- [A Large Language Model Enhanced Conversational Recommender System](https://mlsanity.com/paper/2308.06212/) (2023)
- [Do Large Language Models Rank Fairly? An Empirical Study on the Fairness of LLMs as Rankers](https://mlsanity.com/paper/2404.03192/) (2024)
- [Behavior Alignment: A New Perspective of Evaluating LLM-based Conversational Recommender Systems](https://mlsanity.com/paper/2404.11773/) (2024)
- [On the Benchmarking of LLMs for Open-Domain Dialogue Evaluation](https://mlsanity.com/paper/2407.03841/) (2024)
- [RAMO: Retrieval-Augmented Generation for Enhancing MOOCs Recommendations](https://mlsanity.com/paper/2407.04925/) (2024)
- [ZeQR: Zero-shot Query Reformulation for Conversational Search](https://mlsanity.com/paper/2307.09384/) (2023)
- [Simple but Efficient: A Multi-Scenario Nearline Retrieval Framework for Recommendation on Taobao](https://mlsanity.com/paper/2408.00247/) (2024)

## Built on by (most cited first, 2 of 2)

- [Where and What: Reasoning Dynamic and Implicit Preferences in Situated Conversational Recommendation](https://mlsanity.com/paper/2604.20749/) (2026)
- [Re2A: Situated Conversational Recommendation via Rubric-based Preference Reasoning and Alignment](https://mlsanity.com/paper/2609.18249/) (2026)

## 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.