mlsanityData to 7 Oct 2026

Latent Inter-User Difference Modeling for LLM Personalization

arXiv 2507.20849 ↗First posted 28 Jul 2025cs.CLcited by 20

Not on the map. Why?

Abstract (arXiv)

Large language models (LLMs) are increasingly integrated into users' daily lives, leading to a growing demand for personalized outputs. Previous work focuses on leveraging a user's own history, overlooking inter-user differences that are crucial for effective personalization. While recent work has attempted to model such differences, the reliance on language-based prompts often hampers the effective extraction of meaningful distinctions. To address these issues, we propose Difference-aware Embedding-based Personalization (DEP), a framework that models inter-user differences in the latent space instead of relying on language prompts. DEP constructs soft prompts by contrasting a user's embedding with those of peers who engaged with similar content, highlighting relative behavioral signals. A sparse autoencoder then filters and compresses both user-specific and difference-aware embeddings, preserving only task-relevant features before injecting them into a frozen LLM. Experiments on personalized review generation show that DEP consistently outperforms baseline methods across multiple metrics. Our code is available at https://github.com/SnowCharmQ/DEP.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). Builds on 50 of its 85 references that are in the map. First posted on arXiv 28 Jul 2025.

Builds on

50 of 85 references.

References · 50

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  4. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  5. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
  6. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
  7. 2020Longformer: The Long-Document Transformercited by 3,362
  8. 2023FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioningcited by 2,551
  9. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
  10. 2018A Call for Clarity in Reporting BLEU Scorescited by 1,790
  11. 2023Sparse Autoencoders Find Highly Interpretable Features in Language Modelscited by 1,359
  12. 2019ZeRO: Memory Optimizations Toward Training Trillion Parameter Modelscited by 1,278
38 more
  1. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,203
  2. 2017Neural Collaborative Filteringcited by 1,108
  3. 2019Neural Graph Collaborative Filteringcited by 660
  4. 2023LaMP: When Large Language Models Meet Personalizationcited by 425
  5. 2024AlphaEdit: Null-Space Constrained Knowledge Editing for Language Modelscited by 224
  6. 2024Bridging Language and Items for Retrieval and Recommendation: Benchmarking LLMs as Semantic Encoderscited by 213
  7. 2025Do LLMs Recognize Your Preferences? Evaluating Personalized Preference Following in LLMscited by 142
  8. 2023TaskBench: Benchmarking Large Language Models for Task Automationcited by 138
  9. 2023CoLLM: Integrating Collaborative Embeddings into Large Language Models for Recommendationcited by 99
  10. 2023Pearl: Personalizing Large Language Model Writing Assistants with Generation-Calibrated Retrieverscited by 91
  11. 2023When Large Language Models Meet Personalization: Perspectives of Challenges and Opportunitiescited by 89
  12. 2024User-LLM: Efficient LLM Contextualization with User Embeddingscited by 74
  13. 2025Are Reasoning Models More Prone to Hallucination?cited by 62
  14. 2024PAD: Personalized Alignment of LLMs at Decoding-Timecited by 58
  15. 2023Teach LLMs to Personalize -- An Approach inspired by Writing Educationcited by 48
  16. 2024Persona-DB: Efficient Large Language Model Personalization for Response Prediction with Collaborative Data Refinementcited by 47
  17. 2025Reinforced Latent Reasoning for LLM-based Recommendationcited by 46
  18. 2025Personalized Generation In Large Model Era: A Surveycited by 45
  19. 2025AlphaSteer: Learning Refusal Steering with Principled Null-Space Constraintcited by 45
  20. 2025Measuring What Makes You Unique: Difference-Aware User Modeling for Enhancing LLM Personalizationcited by 44
  21. 2025Personalized Text Generation with Contrastive Activation Steeringcited by 30
  22. 2025NextQuill: Causal Preference Modeling for Enhancing LLM Personalizationcited by 29
  23. 2024User Embedding Model for Personalized Language Promptingcited by 28
  24. 2025Reasoning-Enhanced Self-Training for Long-Form Personalized Text Generationcited by 26
  25. 2024Text-like Encoding of Collaborative Information in Large Language Models for Recommendationcited by 25
  26. 2025Retrieval Augmented Generation with Collaborative Filtering for Personalized Text Generationcited by 23
  27. 2025Beware of Your Po! Measuring and Mitigating AI Safety Risks in Role-Play Fine-Tuning of LLMscited by 22
  28. 2025Teaching Language Models to Evolve with Users: Dynamic Profile Modeling for Personalized Alignmentcited by 22
  29. 2025The Emergence of Abstract Thought in Large Language Models Beyond Any Languagecited by 20
  30. 2025LLM2Rec: Large Language Models Are Powerful Embedding Models for Sequential Recommendationcited by 19
  31. 2025DependEval: Benchmarking LLMs for Repository Dependency Understandingcited by 16
  32. 2025LastingBench: Defend Benchmarks Against Knowledge Leakagecited by 14
  33. 2025DRC: Enhancing Personalized Image Generation via Disentangled Representation Compositioncited by 8
  34. 2025DiscRec: Disentangled Semantic-Collaborative Modeling for Generative Recommendationcited by 8
  35. 2025PEARL: Towards Permutation-Resilient LLMscited by 5
  36. 2025IGD: Token Decisiveness Modeling via Information Gain in LLMs for Personalized Recommendationcited by 5
  37. 2025ComMer: a Framework for Compressing and Merging User Data for Personalizationcited by 3
  38. 2025Improving RAG for Personalization with Author Features and Contrastive Examplescited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 17.

20 papers.

Sort:

By area:

  1. 2025Think-While-Generating: On-the-Fly Reasoning for Personalized Long-Form Generationcited by 29
  2. 2026Toward Personalized LLM-Powered Agents: Foundations, Evaluation, and Future Directionscited by 10
  3. 2025SteerX: Disentangled Steering for LLM Personalizationcited by 7
  4. 2026AlpsBench: An LLM Personalization Benchmark for Real-Dialogue Memorization and Preference Alignmentcited by 6
  5. 2026PERM: Psychology-grounded Empathetic Reward Modeling for Large Language Modelscited by 5
  6. 2025Reinforced Strategy Optimization for Conversational Recommender Systems via Network-of-Expertscited by 4
  7. 2026Know You Before You Speak: User-State Modeling for LLM Personalization in Multi-Turn Conversationcited by 3
  8. 2026Preference-Aware Rubric Learning for Personalized Evaluationcited by 2
  9. 2026Personalizing LLMs with Binary Feedback: A Preference-Corrected Optimization Frameworkcited by 1
  10. 2026LATTE: Forecasting Peer Anchored Preference Trajectories for Personalized LLM Generationcited by 1
  11. 2026Towards Root Memories: Benchmarking and Enhancing Implicit Logical Memory Retrieval for Personalized LLMscited by 1
  12. 2026The Subjectivity of Respect in Police Traffic Stops: Modeling Community Perspectives in Body-Worn Camera Footagecited by 0
8 more
  1. 2026ClusterRAG: Cluster-Based Collaborative Filtering for Personalized Retrieval-Augmented Generationcited by 0
  2. 2026PAFO: Pareto Fairness Optimization for Personalized Reward Modelingcited by 0
  3. 2026Communication Policy Evolution for Proactive LLM Agentscited by 0
  4. 2026Learning to Adapt Cross-Domain Preferences via Meta-LoRA for LLM Personalizationcited by 0
  5. 2026PersonaEdit: Representative Sample Selection for Personalized Model Editingcited by 0
  6. 2026Inferring Hidden User Models from the Behavior of Personalized LLM Agentscited by 0
  7. 2026HyperTrace: Hypothesis-Based Preference Tracing for Online LLM Personalizationcited by 0
  8. 2026Rubric-Aware On-Policy Self-Distillation for LLM Personalizationcited by 0