mlsanityData to 7 Oct 2026

End-to-end Training for Recommendation with Language-based User Profiles

arXiv 2410.18870 ↗First posted 24 Oct 2024cs.IR cs.LGcited by 10

Not on the map. Why?

Abstract (arXiv)

There is a growing interest in natural language-based user profiles for recommender systems, which aims to enhance transparency and scrutability compared with embedding-based methods. Existing studies primarily generate these profiles using zero-shot inference from large language models (LLMs), but their quality remains insufficient, leading to suboptimal recommendation performance. In this paper, we introduce LangPTune, the first end-to-end training framework to optimize LLM-generated user profiles. Our method significantly outperforms zero-shot approaches by explicitly training the LLM for the recommendation objective. Through extensive evaluations across diverse training configurations and benchmarks, we demonstrate that LangPTune not only surpasses zero-shot baselines but can also matches the performance of state-of-the-art embedding-based methods. Finally, we investigate whether the training procedure preserves the interpretability of these profiles compared to zero-shot inference through both GPT-4 simulations and crowdworker user studies. Implementation of LangPTune can be found at https://github.com/ZhaolinGao/LangPTune.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 34 of its 66 references that are in the map. First posted on arXiv 24 Oct 2024.

Builds on

34 of 66 references.

References · 34

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2017Proximal Policy Optimization Algorithmscited by 14,441
  3. 2024The Llama 3 Herd of Modelscited by 14,192
  4. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  5. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  6. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  7. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  8. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  9. 2017Deep reinforcement learning from human preferencescited by 3,846
  10. 2019Fine-Tuning Language Models from Human Preferencescited by 2,124
  11. 2024Gemma 2: Improving Open Language Models at a Practical Sizecited by 1,928
  12. 2020LightGCN: Simplifying and Powering Graph Convolution Network for Recommendationcited by 1,134
22 more
  1. 2019BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformercited by 952
  2. 2023Can Large Language Models Be an Alternative to Human Evaluations?cited by 729
  3. 2022Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5)cited by 396
  4. 2023TALLRec: An Effective and Efficient Tuning Framework to Align Large Language Model with Recommendationcited by 336
  5. 2024Bridging Language and Items for Retrieval and Recommendation: Benchmarking LLMs as Semantic Encoderscited by 213
  6. 2023Is ChatGPT a Good Recommender? A Preliminary Studycited by 192
  7. 2023Representation Learning with Large Language Models for Recommendationcited by 155
  8. 2023Do LLMs Understand User Preferences? Evaluating LLMs On User Rating Predictioncited by 113
  9. 2023CoLLM: Integrating Collaborative Embeddings into Large Language Models for Recommendationcited by 99
  10. 2023PALR: Personalization Aware LLMs for Recommendationcited by 96
  11. 2023Leveraging Large Language Models for Sequential Recommendationcited by 78
  12. 2023Large Language Models are Competitive Near Cold-start Recommenders for Language- and Item-based Preferencescited by 66
  13. 2024REBEL: Reinforcement Learning via Regressing Relative Rewardscited by 66
  14. 2023GenRec: Large Language Model for Generative Recommendationcited by 62
  15. 2023LLaRA: Large Language-Recommendation Assistantcited by 56
  16. 2020Simplify and Robustify Negative Sampling for Implicit Collaborative Filteringcited by 34
  17. 2024Transparent and Scrutable Recommendations Using Natural Language User Profilescited by 24
  18. 2022On Natural Language User Profiles for Transparent and Scrutable Recommendationcited by 23
  19. 2024Language-Based User Profiles for Recommendationcited by 17
  20. 2024Sequential Recommendation with Latent Relations based on Large Language Modelcited by 17
  21. 2023Editable User Profiles for Controllable Text Recommendationcited by 16
  22. 2023CTRL: Connect Collaborative and Language Model for CTR Predictioncited by 14

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 6; 2026: 3.

10 papers.

  1. 2025R2ec: Towards Large Recommender Models with Reasoningcited by 13
  2. 2025Interactive Recommendation Agent with Active User Commandscited by 10
  3. 2024TEARS: Textual Representations for Scrutable Recommendationscited by 5
  4. 2025POPI: Personalizing LLMs via Optimized Natural Language Preference Inferencecited by 5
  5. 2025CTRL-Rec: Controlling Recommender Systems With Natural Languagecited by 4
  6. 2026GISTBench: Evaluating LLM User Understanding via Evidence-Based Interest Verificationcited by 3
  7. 2026Language Models Don't Know What You Want: Evaluating Personalization in Deep Research Needs Real Userscited by 2
  8. 2025Music Recommendation with Large Language Models: Challenges, Opportunities, and Evaluationcited by 1
  9. 2026High Fidelity Textual User Representation over Heterogeneous Sources via Reinforcement Learningcited by 1
  10. 2025Co-Authoring the Self: A Human-AI Interface for Interest Reflection in Recommenderscited by 0