ReGeS: Reciprocal Retrieval-Generation Synergy for Conversational Recommender Systems

• URL: http://arxiv.org/abs/2509.21371v1
• Date: Mon, 22 Sep 2025 17:47:57 GMT
• Title: ReGeS: Reciprocal Retrieval-Generation Synergy for Conversational Recommender Systems
• Authors: Dayu Yang, Hui Fang,
• Abstract summary: ReGeS is a reciprocal Retrieval-Generation Synergy framework that unifies generation-augmented retrieval and retrieval-augmented generation.<n>ReGeS achieves state-of-the-art performance in recommendation accuracy, demonstrating the effectiveness of reciprocal synergy for knowledge-intensive CRS tasks.
• Score: 5.2284572339698645
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• CESRec: Constructing Pseudo Interactions for Sequential Recommendation via Conversational Feedback [39.53651863631003]
  We propose a novel framework that integrates the long-term preference modeling of Sequential Recommendation Systems (SRS) with the real-time preference elicitation of Conversational Recommendation Systems (CRS)<n>We introduce semantic-based pseudo interaction construction, which dynamically updates users'historical interaction sequences by analyzing conversational feedback, generating a pseudo-interaction sequence that seamlessly combines long-term and real-time preferences.
  arXiv  Detail & Related papers  (2025-09-11T10:56:40Z)
• Hybrid AI for Responsive Multi-Turn Online Conversations with Novel Dynamic Routing and Feedback Adaptation [2.4830284216463]
  This paper introduces a novel hybrid framework that integrates RAG with intent-based canned responses.<n>Our framework employs a dialogue context manager to ensure coherence in multi-turn interactions and incorporates a feedback loop to refine intents.<n> Experimental results demonstrate that the proposed framework achieves a balance of high accuracy (95%) and low latency (180ms)
  arXiv  Detail & Related papers  (2025-06-02T17:59:27Z)
• Self-Routing RAG: Binding Selective Retrieval with Knowledge Verbalization [95.85537087475882]
  Existing approaches underutilize the inherent knowledge of large language models (LLMs)<n>We propose Self-Routing RAG, a novel framework that binds selective retrieval with knowledge verbalization.<n> SR-RAG reduces the number of retrievals by 29% while improving performance by 5.1%.
  arXiv  Detail & Related papers  (2025-04-01T17:59:30Z)
• Graph Retrieval-Augmented LLM for Conversational Recommendation Systems [52.35491420330534]
  G-CRS (Graph Retrieval-Augmented Large Language Model for Conversational Recommender Systems) is a training-free framework that combines graph retrieval-augmented generation and in-context learning.<n>G-CRS achieves superior recommendation performance compared to existing methods without requiring task-specific training.
  arXiv  Detail & Related papers  (2025-03-09T03:56:22Z)
• Unanswerability Evaluation for Retrieval Augmented Generation [74.3022365715597]
  UAEval4RAG is a framework designed to evaluate whether RAG systems can handle unanswerable queries effectively.<n>We define a taxonomy with six unanswerable categories, and UAEval4RAG automatically synthesizes diverse and challenging queries.
  arXiv  Detail & Related papers  (2024-12-16T19:11:55Z)
• Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection [74.51523859064802]
  We introduce a new framework called Self-Reflective Retrieval-Augmented Generation (Self-RAG) Self-RAG enhances an LM's quality and factuality through retrieval and self-reflection. It significantly outperforms state-of-the-art LLMs and retrieval-augmented models on a diverse set of tasks.
  arXiv  Detail & Related papers  (2023-10-17T18:18:32Z)
• PICK: Polished & Informed Candidate Scoring for Knowledge-Grounded Dialogue Systems [59.1250765143521]
  Current knowledge-grounded dialogue systems often fail to align the generated responses with human-preferred qualities. We propose Polished & Informed Candidate Scoring (PICK), a generation re-scoring framework. We demonstrate the effectiveness of PICK in generating responses that are more faithful while keeping them relevant to the dialogue history.
  arXiv  Detail & Related papers  (2023-09-19T08:27:09Z)
• Conversational Recommendation as Retrieval: A Simple, Strong Baseline [4.737923227003888]
  Conversational recommendation systems (CRS) aim to recommend suitable items to users through natural language conversation. Most CRS approaches do not effectively utilize the signal provided by these conversations. We propose an alternative information retrieval (IR)-styled approach to the CRS item recommendation task.
  arXiv  Detail & Related papers  (2023-05-23T06:21:31Z)
• EGCR: Explanation Generation for Conversational Recommendation [7.496434082286226]
  Explanation Generation for Conversational Recommendation (EGCR) based on generating explanations for conversational agents to explain why they make the action. EGCR incorporates user reviews to enhance the item representation and increase the informativeness of the whole conversation. We evaluate EGCR on one benchmark conversational recommendation datasets and achieve better performance on both recommendation accuracy and conversation quality than other state-of-the art models.
  arXiv  Detail & Related papers  (2022-08-17T02:30:41Z)
• KECRS: Towards Knowledge-Enriched Conversational Recommendation System [50.0292306485452]
  chit-chat-based conversational recommendation systems (CRS) provide item recommendations to users through natural language interactions. external knowledge graphs (KG) have been introduced into chit-chat-based CRS. We propose the Knowledge-Enriched Conversational Recommendation System (KECRS) Experimental results on a large-scale dataset demonstrate that KECRS outperforms state-of-the-art chit-chat-based CRS.
  arXiv  Detail & Related papers  (2021-05-18T03:52:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.