Lune

EMNLP Findings2025

Leveraging Unpaired Feedback for Long-Term LLM-based Recommendation Tuning

Jizhi Zhang, Chongming Gao, Wentao Shi, Xi-Lin Chen, Jingang Wang, Xunliang Cai, Fuli Feng

Abstract

Most recommender systems focus on shortterm objectives such as click-through rate, often at the expense of long-term user satisfaction. This can lead to echo chambers, where users are repeatedly exposed to redundant content. While recent efforts integrate Large Language Models (LLMs) into recommendation, they typically inherit this shortsighted focus. In this work, we highlight unpaired feedback-implicit signals such as continued engagement (positive) or silent disengagement (negative) that lack explicit contrastive labels-as a key challenge for longterm recommendation. Effectively learning from such feedback is crucial for improving LLM-based recommenders in dynamic user environments. To this end, we propose UL-Rec (Unpaired Feedback for Long-Term LLMbased Recommendation Tuning), a simple framework that fine-tunes LLMs using both positive and negative unpaired feedback. UL-Rec leverages the KTO algorithm to incorporate these signals without requiring paired supervision. Despite its simplicity, ULRec consistently improves long-term recommendation performance, demonstrating the value of modeling unpaired user feedback.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

1 top-tier paper has cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers1

  1. Uncertainty-aware Generative RecommendationChenxiao Fan, Chongming Gao, Yaxin Gong, Haoyan Liu et al.KDD 2026 · 2 citations

Builds on12

  1. Conservative Q-Learning for Offline Reinforcement LearningAviral Kumar, Aurick Zhou, George Tucker, Sergey LevineNeurIPS 2020 · 2,881 citations
  2. Efficient Memory Management for Large Language Model Serving with PagedAttentionWoosuk Kwon, Zhuohan Li, Siyuan Zhuang, Ying Sheng et al.SOSP 2023 · 1,016 citations
  3. Model Alignment as Prospect Theoretic OptimizationKawin Ethayarajh, Winnie Xu, Niklas Muennighoff, Dan Jurafsky et al.ICML 2024 · 973 citations
  4. Critic Regularized RegressionZiyu Wang, Alexander Novikov, Konrad Zolna, Josh Merel et al.NeurIPS 2020 · 406 citations
  5. Self-Supervised Reinforcement Learning for Recommender SystemsXin Xin, Alexandros Karatzoglou, Ioannis Arapakis, Joemon M. JoseSIGIR 2020 · 217 citations

Related papers

  1. What Makes LLMs Effective Sequential Recommenders? A Study on Preference Intensity and Temporal ContextZhongyu Ouyang, Qianlong Wen, Chunhui Zhang, Yanfang Ye et al.ACL 2026
  2. Tunable LLM-based Proactive Recommendation AgentMingze Wang, Chongming Gao, Wenjie Wang, Yangyang Li et al.ACL 2025 · 4 citations
  3. Customizing In-context Learning for Dynamic Interest Adaption in LLM-based RecommendationKeqin Bao, Ming Yan, Yang Zhang, Jizhi Zhang et al.ACL Findings 2025 · 1 citation
  4. Transparent and Scrutable Recommendations Using Natural Language User ProfilesJerome Ramos, Hossein A. Rahmani, Xi Wang, Xiao Fu et al.ACL 2024
  5. ProEx: A Unified Framework Leveraging Large Language Model with Profile Extrapolation for RecommendationYi Zhang, Yiwen Zhang, Yu Wang, Tong Chen et al.KDD 2026 · 1 citation
Dusk over the sea between two cliffs drawn in fine vertical lines