mlsanityData to 14 Oct 2026

HYDRA: Model Factorization Framework for Black-Box LLM Personalization

arXiv 2406.02888 ↗First posted 5 Jun 2024cs.CL cs.AI cs.LGcited by 60

Not on the map. Why?

Abstract (arXiv)

Personalization has emerged as a critical research area in modern intelligent systems, focusing on mining users' behavioral history and adapting to their preferences for delivering tailored experiences. Despite the remarkable few-shot capabilities exhibited by black-box large language models (LLMs), the inherent opacity of their model parameters presents significant challenges in aligning the generated output with individual expectations. Existing solutions have primarily focused on prompt design to incorporate user-specific profiles and behaviors; however, such approaches often struggle to generalize effectively due to their inability to capture shared knowledge among all users. To address these challenges, we propose HYDRA, a model factorization framework that captures both user-specific behavior patterns from historical data and shared general knowledge among all users to deliver personalized generation. In order to capture user-specific behavior patterns, we first train a reranker to prioritize the most useful information from top-retrieved relevant historical records. By combining the prioritized history with the corresponding query, we train an adapter to align the output with individual user-specific preferences, eliminating the reliance on access to inherent model parameters of black-box LLMs. Both the reranker and the adapter can be decomposed into a base model with multiple user-specific heads, resembling a hydra. The base model maintains shared knowledge across users, while the multiple personal heads capture user-specific preferences. Experimental results demonstrate that HYDRA outperforms existing state-of-the-art prompt-based methods by an average relative improvement of 9.01% across five diverse personalization tasks in the LaMP benchmark. Our implementation is available at https://github.com/night-chen/HYDRA.

Key facts. Cited by 60 papers in the map (data through 14 Oct 2026). Builds on 51 of its 71 references that are in the map. First posted on arXiv 5 Jun 2024.

Builds on

51 of 71 references.

References · 51

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2023GPT-4 Technical Reportcited by 18,396
  4. 2022Training language models to follow instructions with human feedbackcited by 15,971
  5. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  6. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  7. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  8. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
  9. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,236
  10. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,780
  11. 2020Longformer: The Long-Document Transformercited by 3,413
  12. 2020Learning to summarize from human feedbackcited by 2,588
38 more
  1. 2019Fine-Tuning Language Models from Human Preferencescited by 2,150
  2. 2020Don't Stop Pretraining: Adapt Language Models to Domains and Taskscited by 1,565
  3. 2021DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharingcited by 1,254
  4. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,216
  5. 2023Whose Opinions Do Language Models Reflect?cited by 773
  6. 2023Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedbackcited by 759
  7. 2023LaMP: When Large Language Models Meet Personalizationcited by 437
  8. 2023Fine-Grained Human Feedback Gives Better Rewards for Language Model Trainingcited by 401
  9. 2023A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Uglycited by 387
  10. 2023Large Language Models are Zero-Shot Rankers for Recommender Systemscited by 309
  11. 2023Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Mergingcited by 280
  12. 2023ToolQA: A Dataset for LLM Question Answering with External Toolscited by 274
  13. 2024Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Securitycited by 260
  14. 2022Black-Box Tuning for Language-Model-as-a-Servicecited by 256
  15. 2023AdaPlanner: Adaptive Planning from Feedback with Language Modelscited by 196
  16. 2023Is ChatGPT a Good Recommender? A Preliminary Studycited by 193
  17. 2023Recommender Systems in the Era of Large Language Models (LLMs)cited by 189
  18. 2023Uncovering ChatGPT's Capabilities in Recommender Systemscited by 161
  19. 2023ToolChain*: Efficient Action Space Navigation in Large Language Models with A* Searchcited by 105
  20. 2024Optimization Methods for Personalizing Large Language Models through Retrieval Augmentationcited by 99
  21. 2023Pearl: Personalizing Large Language Model Writing Assistants with Generation-Calibrated Retrieverscited by 92
  22. 2024Democratizing Large Language Models via Personalized Parameter-Efficient Fine-tuningcited by 90
  23. 2023Personalisation within bounds: A risk taxonomy and policy framework for the alignment of large language models with personalised feedbackcited by 87
  24. 2024EHRAgent: Code Empowers Large Language Models for Few-shot Complex Tabular Reasoning on Electronic Health Recordscited by 78
  25. 2023LLM-Rec: Personalized Recommendation via Prompting Large Language Modelscited by 77
  26. 2023ONCE: Boosting Content-based Recommendation with Both Open- and Closed-source Large Language Modelscited by 54
  27. 2023Teach LLMs to Personalize -- An Approach inspired by Writing Educationcited by 48
  28. 2023LLMCad: Fast and Scalable On-device Large Language Model Inferencecited by 45
  29. 2023Integrating Summarization and Retrieval for Enhanced Personalization via Large Language Modelscited by 45
  30. 2024BMRetriever: Tuning Large Language Models as Better Biomedical Text Retrieverscited by 38
  31. 2024MedAdapter: Efficient Test-Time Adaptation of Large Language Models towards Medical Reasoningcited by 36
  32. 2023CombLM: Adapting Black-Box Language Models through Small Fine-Tuned Modelscited by 26
  33. 2023Large Language Models for User Interest Journeyscited by 24
  34. 2023BookGPT: A General Framework for Book Recommendation Empowered by Large Language Modelcited by 22
  35. 2024RAM-EHR: Retrieval Augmentation Meets Clinical Predictions on Electronic Health Recordscited by 21
  36. 2023Knowledge-Infused Prompting: Assessing and Advancing Clinical Text Data Generation with Large Language Modelscited by 20
  37. 2023kNN-Adapter: Efficient Domain Adaptation for Black-Box Language Modelscited by 14
  38. 2023PolyIE: A Dataset of Information Extraction from Polymer Material Scientific Literaturecited by 13

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 7; 2025: 30; 2026: 23.

60 papers.

Sort:

By area:

  1. 2025Do LLMs Recognize Your Preferences? Evaluating Personalized Preference Following in LLMscited by 148
  2. 2024Personalized Pieces: Efficient Personalized Large Language Models through Collaborative Effortscited by 74
  3. 2025A Survey of Personalized Large Language Models: Progress and Future Directionscited by 71
  4. 2025Measuring What Makes You Unique: Difference-Aware User Modeling for Enhancing LLM Personalizationcited by 45
  5. 2024Personality Alignment of Large Language Modelscited by 36
  6. 2025Personalized Text Generation with Contrastive Activation Steeringcited by 34
  7. 2024AI PERSONA: Towards Life-long Personalization of LLMscited by 32
  8. 2025Think-While-Generating: On-the-Fly Reasoning for Personalized Long-Form Generationcited by 30
  9. 2025SynthesizeMe! Inducing Persona-Guided Prompts for Personalized Reward Models in LLMscited by 29
  10. 2025A Survey on Personalized and Pluralistic Preference Alignment in Large Language Modelscited by 27
  11. 2025A Survey of Personalization: From RAG to Agentcited by 27
  12. 2025Teaching Language Models to Evolve with Users: Dynamic Profile Modeling for Personalized Alignmentcited by 24
38 more
  1. 2024On the Way to LLM Personalization: Learning to Remember User Conversationscited by 21
  2. 2025Collab-RAG: Boosting Retrieval-Augmented Generation for Complex Question Answering via White-Box and Black-Box LLM Collaborationcited by 20
  3. 2025Instant Personalized Large Language Model Adaptation via Hypernetworkcited by 18
  4. 2025Adaptive Graph of Thoughts: Test-Time Adaptive Reasoning Unifying Chain, Tree, and Graph Structurescited by 16
  5. 2025Personalized Safety in LLMs: A Benchmark and A Planning-Based Agent Approachcited by 16
  6. 2025Personalize Your LLM: Fake it then Align itcited by 15
  7. 2025MMPB: It's Time for Multi-Modal Personalizationcited by 14
  8. 2025Personalized LLM Decoding via Contrasting Personal Preferencecited by 12
  9. 2026VitaBench 2.0: Evaluating Personalized and Proactive Agents in Long-Term User Interactionscited by 12
  10. 2025Aligning LLMs by Predicting Preferences from User Writing Samplescited by 11
  11. 2026PersonaVLM: Long-Term Personalized Multimodal LLMscited by 11
  12. 2025Embedding-to-Prefix: Parameter-Efficient Personalization for Pre-Trained Large Language Modelscited by 10
  13. 2024Matryoshka Pilot: Learning to Drive Black-Box LLMs with LLMscited by 9
  14. 2025SteerX: Disentangled Steering for LLM Personalizationcited by 7
  15. 2026Me-Agent: A Personalized Mobile Agent with Two-Level User Habit Learning for Enhanced Interactioncited by 7
  16. 2025USER-VLM 360: Personalized Vision Language Models with User-aware Tuning for Social Human-Robot Interactionscited by 6
  17. 2026Your Language Model Secretly Contains Personality Subnetworkscited by 5
  18. 2025Reasoning LLMs for User-Aware Multimodal Conversational Agentscited by 4
  19. 2026Synthetic Interaction Data for Scalable Personalization in Large Language Modelscited by 4
  20. 2024PREDICT: Preference Reasoning by Evaluating Decomposed preferences Inferred from Candidate Trajectoriescited by 3
  21. 2025Improving RAG for Personalization with Author Features and Contrastive Examplescited by 3
  22. 2025RPM: Reasoning-Level Personalization for Black-Box Large Language Modelscited by 3
  23. 2025Tagging the Thought: Unlocking Personalization Reasoning via Reinforcement Learningcited by 3
  24. 2025MENLO: From Preferences to Proficiency -- Evaluating and Modeling Native-like Quality Across 47 Languagescited by 3
  25. 2026CARD: Cluster-level Adaptation with Reward-guided Decoding for Personalized Text Generationcited by 3
  26. 2026Beyond Retrieval: Learning Compact User Representations for Scalable LLM Personalizationcited by 3
  27. 2025AdaRewriter: Unleashing the Power of Prompting-based Conversational Query Reformulation via Test-Time Adaptationcited by 2
  28. 2025A Survey on Training-free Alignment of Large Language Modelscited by 2
  29. 2025Fints: Efficient Inference-Time Personalization for LLMs with Fine-Grained Instance-Tailored Steeringcited by 2
  30. 2026Preference-Aware Rubric Learning for Personalized Evaluationcited by 2
  31. 2024Multi-Dimensional Insights: Benchmarking Real-World Personalization in Large Multimodal Modelscited by 1
  32. 2025IP-Dialog: Evaluating Implicit Personalization in Dialogue Systems with Synthetic Datacited by 1
  33. 2026CoPA: Benchmarking Personalized Question Answering with Data-Informed Cognitive Factorscited by 1
  34. 2026LATTE: Forecasting Peer Anchored Preference Trajectories for Personalized LLM Generationcited by 1
  35. 2026Self-supervised User Profile Generation for Personalizationcited by 1
  36. 2026Re-Centering Humans in LLM Personalizationcited by 1
  37. 2025Reflective Personalization Optimization: A Post-hoc Rewriting Framework for Black-Box Large Language Modelscited by 0
  38. 2026Do Implicit Personalization and Explicit Styles Conflict? PsPLUG: A Lightweight Plug-in for Balancing Personalization and Style in Customized LLMscited by 0

50 most cited of 60 All 60 (JSON)