mlsanityData to 14 Oct 2026

USB-Rec: An Effective Framework for Improving Conversational Recommendation Capability of Large Language Model

arXiv 2509.20381 ↗First posted 20 Sep 2025cs.CL cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Recently, Large Language Models (LLMs) have been widely employed in Conversational Recommender Systems (CRSs). Unlike traditional language model approaches that focus on training, all existing LLMs-based approaches are mainly centered around how to leverage the summarization and analysis capabilities of LLMs while ignoring the issue of training. Therefore, in this work, we propose an integrated training-inference framework, User-Simulator-Based framework (USB-Rec), for improving the performance of LLMs in conversational recommendation at the model level. Firstly, we design a LLM-based Preference Optimization (PO) dataset construction strategy for RL training, which helps the LLMs understand the strategies and methods in conversational recommendation. Secondly, we propose a Self-Enhancement Strategy (SES) at the inference stage to further exploit the conversational recommendation potential obtained from RL training. Extensive experiments on various datasets demonstrate that our method consistently outperforms previous state-of-the-art methods.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 42 of its 52 references that are in the map. First posted on arXiv 20 Sep 2025.

Builds on

42 of 52 references.

References · 42

  1. 2022Training language models to follow instructions with human feedbackcited by 15,971
  2. 2024The Llama 3 Herd of Modelscited by 14,715
  3. 2024Qwen2.5 Technical Reportcited by 4,942
  4. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,988
  5. 2024LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Modelscited by 1,464
  6. 2024ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Toolscited by 1,121
  7. 2023A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivitycited by 894
  8. 2022Towards Reasoning in Large Language Models: A Surveycited by 596
  9. 2023Is ChatGPT a General-Purpose Natural Language Processing Task Solver?cited by 488
  10. 2023A Survey on Large Language Models for Recommendationcited by 379
  11. 2023TALLRec: An Effective and Efficient Tuning Framework to Align Large Language Model with Recommendationcited by 337
  12. 2023Chat-REC: Towards Interactive and Explainable LLMs-Augmented Recommender Systemcited by 242
30 more
  1. 2023Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Futurecited by 184
  2. 2018Towards Deep Conversational Recommendationscited by 176
  3. 2020A Survey on Conversational Recommender Systemscited by 143
  4. 2024Attacks, Defenses and Evaluations for LLM Conversation Safety: A Surveycited by 130
  5. 2023Large Language Models as Zero-Shot Conversational Recommenderscited by 127
  6. 2020Improving Conversational Recommender Systems via Knowledge Graph based Semantic Fusioncited by 122
  7. 2018Conversational Recommender Systemcited by 115
  8. 2019Towards Knowledge-Based Recommender Dialog Systemcited by 113
  9. 2024Data-efficient Fine-tuning for LLM-based Recommendationcited by 104
  10. 2023PALR: Personalization Aware LLMs for Recommendationcited by 96
  11. 2020Towards Topic-Guided Conversational Recommender Systemcited by 94
  12. 2023When Large Language Models Meet Personalization: Perspectives of Challenges and Opportunitiescited by 90
  13. 2022Towards Unified Conversational Recommender Systems via Knowledge-Enhanced Prompt Learningcited by 86
  14. 2023Let the LLMs Talk: Simulating Human-to-Human Conversational QA via Zero-Shot LLM-to-LLM Interactionscited by 70
  15. 2023GenRec: Large Language Model for Generative Recommendationcited by 63
  16. 2023LLaRA: Large Language-Recommendation Assistantcited by 56
  17. 2023Rethinking the Evaluation for Conversational Recommendation in the Era of Large Language Modelscited by 48
  18. 2019Recommendation as a Communication Game: Self-Supervised Bot-Play for Goal-oriented Dialoguecited by 44
  19. 2022A Unified Multi-task Learning Framework for Multi-goal Conversational Recommender Systemscited by 32
  20. 2023LLMRec: Benchmarking Large Language Models on Recommendation Taskcited by 30
  21. 2022User-Centric Conversational Recommendation with Multi-Aspect User Modelingcited by 29
  22. 2024QueryAgent: A Reliable and Efficient Reasoning Framework with Environmental Feedback-based Self-Correctioncited by 27
  23. 2024How Reliable is Your Simulator? Analysis on the Limitations of Current LLM-based User Simulators for Conversational Recommendationcited by 27
  24. 2024Analyzing LLM Behavior in Dialogue Summarization: Unveiling Circumstantial Hallucination Trendscited by 25
  25. 2022Variational Reasoning over Incomplete Knowledge Graphs for Conversational Recommendationcited by 22
  26. 2022BARCOR: Towards A Unified Framework for Conversational Recommendation Systemscited by 21
  27. 2024MemoCRS: Memory-enhanced Sequential Conversational Recommender Systems with Large Language Modelscited by 17
  28. 2023Improving Conversational Recommendation Systems via Bias Analysis and Language-Model-Enhanced Data Augmentationcited by 11
  29. 2024Behavior Alignment: A New Perspective of Evaluating LLM-based Conversational Recommender Systemscited by 11
  30. 2024SEER: Facilitating Structured Reasoning and Explanation via Reinforcement Learningcited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Graph Retrieval-Augmented LLM for Conversational Recommendation Systems
  2. 2023Leveraging Large Language Models for Pre-trained Recommender Systems
  3. 2026User Simulator-Guided Multi-Turn Preference Optimization for Reasoning LLM-based Conversational Recommendation
  4. 2024Large Language Model Driven Recommendation
  5. 2025A Comprehensive Review on Harnessing Large Language Models to Overcome Recommender System Challenges
  6. 2023A Large Language Model Enhanced Conversational Recommender System
  7. 2025Rank-GRPO: Training LLM-based Conversational Recommender Systems with Reinforcement Learning
  8. 2024Towards Next-Generation LLM-based Recommender Systems: A Survey and Beyond