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

arXiv: https://arxiv.org/abs/2406.00033 · HTML: https://mlsanity.com/paper/2406.00033/

## Key facts

- Cited by 18 papers in the map (data through 14 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.

## Placed in

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

## Builds on (most cited first, 13 of 13)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Efficiently Teaching an Effective Dense Retriever with Balanced Topic Aware Sampling](https://mlsanity.com/paper/2104.06967/) (2021)
- [A Survey on Conversational Recommender Systems](https://mlsanity.com/paper/2004.00646/) (2020)
- [Conversational Recommender System](https://mlsanity.com/paper/1806.03277/) (2018)
- [A Review of Modern Recommender Systems Using Generative Models (Gen-RecSys)](https://mlsanity.com/paper/2404.00579/) (2024)
- ["I'd rather just go to bed": Understanding Indirect Answers](https://mlsanity.com/paper/2010.03450/) (2020)
- [Bayesian Optimization with LLM-Based Acquisition Functions for Natural Language Preference Elicitation](https://mlsanity.com/paper/2405.00981/) (2024)
- [Conversation as Action Under Uncertainty](https://mlsanity.com/paper/1301.3883/) (2013)
- [Self-Supervised Contrastive BERT Fine-tuning for Fusion-based Reviewed-Item Retrieval](https://mlsanity.com/paper/2308.00762/) (2023)
- [Design Patterns for Fusion-Based Object Retrieval](https://mlsanity.com/paper/1708.08715/) (2017)
- [Resolving Indirect Referring Expressions for Entity Selection](https://mlsanity.com/paper/2212.10933/) (2022)

## Built on by (most cited first, 18 of 18)

- [Elaborative Subtopic Query Reformulation for Broad and Indirect Queries in Travel Destination Recommendation](https://mlsanity.com/paper/2410.01598/) (2024)
- [Retrieval-Augmented Purifier for Robust LLM-Empowered Recommendation](https://mlsanity.com/paper/2504.02458/) (2025)
- [Autonomous Information Seeking: A Roadmap for Agentic Recommender Systems](https://mlsanity.com/paper/2607.04433/) (2026)
- [Retrieval Augmented Conversational Recommendation with Reinforcement Learning](https://mlsanity.com/paper/2604.04457/) (2026)
- [WebRec: Enhancing LLM-based Recommendations with Attention-guided RAG from Web](https://mlsanity.com/paper/2511.14182/) (2025)
- [Multi-Type Context-Aware Conversational Recommender Systems via Mixture-of-Experts](https://mlsanity.com/paper/2504.13655/) (2025)
- [Augment or Not? A Comparative Study of Pure and Augmented Large Language Model Recommenders](https://mlsanity.com/paper/2505.23053/) (2025)
- [Catalog-Native LLM: Speaking Item-ID Dialect with Less Entanglement for Recommendation](https://mlsanity.com/paper/2510.05125/) (2025)
- [U-CAN: Utility-Aware Contrastive Attenuation for Efficient Unlearning in Generative Recommendation](https://mlsanity.com/paper/2602.23400/) (2026)
- [TRACE: A Conversational Framework for Sustainable Tourism Recommendation with Agentic Counterfactual Explanations](https://mlsanity.com/paper/2604.14223/) (2026)
- [TRACE: Tourism Recommendation with Accountable Citation Evidence](https://mlsanity.com/paper/2605.07677/) (2026)
- [Large Language Model Driven Recommendation](https://mlsanity.com/paper/2408.10946/) (2024)
- [LatentCRS: A Variational EM Framework for Bridging Semantics and Behavior in LLM-based Conversational Recommendation](https://mlsanity.com/paper/2503.10703/) (2025)
- [Beyond Factual Correctness: Mitigating Preference-Inconsistent Explanations in Explainable Recommendation](https://mlsanity.com/paper/2603.03080/) (2026)
- [NBQ: Next-Best-Question for Dynamic Profiling](https://mlsanity.com/paper/2606.00809/) (2026)
- [Two Views, One Voice: Evidence-Grounded Conversational Music Recommendation](https://mlsanity.com/paper/2607.24846/) (2026)
- [Shape Your Feed: An LLM-based Agentic System for Conversational Recommendation](https://mlsanity.com/paper/2608.06632/) (2026)
- [Towards Effective Structured Context Modeling for Conversational Recommender Systems via Dual-node Monte Carlo Tree Search](https://mlsanity.com/paper/2609.00618/) (2026)

## 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.