mlsanityData to 13 Oct 2026

Text as a Universal Interface for Transferable Personalization

arXiv 2601.04963 ↗First posted 8 Jan 2026cs.CL cs.AIcited by 2

Not on the map. Why?

Abstract (arXiv)

We study the problem of personalization in large language models (LLMs). Prior work predominantly represents user preferences as implicit, model-specific vectors or parameters, yielding opaque ``black-box'' profiles that are difficult to interpret and transfer across models and tasks. In contrast, we advocate natural language as a universal, model- and task-agnostic interface for preference representation. The formulation leads to interpretable and reusable preference descriptions, while naturally supporting continual evolution as new interactions are observed. To learn such representations, we introduce a two-stage training framework that combines supervised fine-tuning on high-quality synthesized data with reinforcement learning to optimize long-term utility and cross-task transferability. Based on this framework, we develop AlignXplore+, a universal preference reasoning model that generates textual preference summaries. Experiments on nine benchmarks show that our 8B model achieves state-of-the-art performanc -- outperforming substantially larger open-source models -- while exhibiting strong transferability across tasks, model families, and interaction formats.

Key facts. Cited by 2 papers in the map (data through 13 Oct 2026). Builds on 32 of its 53 references that are in the map. First posted on arXiv 8 Jan 2026.

Builds on

32 of 53 references.

References · 32

  1. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,213
  2. 2018Self-Attentive Sequential Recommendationcited by 1,175
  3. 2020LightGCN: Simplifying and Powering Graph Convolution Network for Recommendationcited by 1,135
  4. 2018Personalizing Dialogue Agents: I have a dog, do you have pets too?cited by 824
  5. 2019Neural Graph Collaborative Filteringcited by 660
  6. 2023LaMP: When Large Language Models Meet Personalizationcited by 430
  7. 2023TALLRec: An Effective and Efficient Tuning Framework to Align Large Language Model with Recommendationcited by 336
  8. 2023Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Mergingcited by 275
  9. 2021Beyond Goldfish Memory: Long-Term Open-Domain Conversationcited by 267
  10. 2016A Persona-Based Neural Conversation Modelcited by 223
  11. 2025Know Me, Respond to Me: Benchmarking LLMs for Dynamic User Profiling and Personalized Responses at Scalecited by 169
  12. 2018Multi-task Deep Reinforcement Learning with PopArtcited by 139
20 more
  1. 2024Hello Again! LLM-powered Personalized Agent for Long-term Dialoguecited by 121
  2. 2023Do LLMs Understand User Preferences? Evaluating LLMs On User Rating Predictioncited by 114
  3. 2024Optimization Methods for Personalizing Large Language Models through Retrieval Augmentationcited by 99
  4. 2024Decoding-Time Language Model Alignment with Multiple Objectivescited by 93
  5. 2023Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinementcited by 89
  6. 2024User-LLM: Efficient LLM Contextualization with User Embeddingscited by 75
  7. 2024RLHF from Heterogeneous Feedback via Personalization and Preference Aggregationcited by 73
  8. 2024Personalized Pieces: Efficient Personalized Large Language Models through Collaborative Effortscited by 73
  9. 2024PAD: Personalized Alignment of LLMs at Decoding-Timecited by 58
  10. 2023The Past, Present and Better Future of Feedback Learning in Large Language Models for Subjective Human Preferences and Valuescited by 54
  11. 2023Teach LLMs to Personalize -- An Approach inspired by Writing Educationcited by 48
  12. 2025A Survey on Personalized Alignment -- The Missing Piece for Large Language Models in Real-World Applicationscited by 41
  13. 2025Personalized Text Generation with Contrastive Activation Steeringcited by 32
  14. 2025From 1,000,000 Users to Every User: Scaling Up Personalized Preference for User-level Alignmentcited by 30
  15. 2020An analysis on the use of autoencoders for representation learning: fundamentals, learning task case studies, explainability and challengescited by 12
  16. 2025Learning to summarize user information for personalized reinforcement learning from human feedbackcited by 9
  17. 2024CoRA: Collaborative Information Perception by Large Language Model's Weights for Recommendationcited by 7
  18. 2025Extended Inductive Reasoning for Personalized Preference Inference from Behavioral Signalscited by 5
  19. 2025POPI: Personalizing LLMs via Optimized Natural Language Preference Inferencecited by 5
  20. 2025Hard Negative Sampling via Large Language Models for Recommendationcited by 2

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Hypotheses-Guided Self Distillation for Continual Personalizationcited by 1
  2. 2026Learning Preference Adaptation for Large Language Model Personalization via Verbal Reinforcement Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Unsupervised Human Preference Learning
  2. 2024Orchestrating LLMs with Different Personalizations
  3. 2024Disentangling Preference Representation and Text Generation for Efficient Individual Preference Alignment
  4. 2026Preference Heads in Large Language Models: A Mechanistic Framework for Interpretable Personalization
  5. 2025When Personalization Meets Reality: A Multi-Faceted Analysis of Personalized Preference Learning
  6. 2026Large Language Models Should Learn Personalized Rather Than Aggregated Human Preferences
  7. 2026HyperTrace: Hypothesis-Based Preference Tracing for Online LLM Personalization
  8. 2024BAPO: Base-Anchored Preference Optimization for Overcoming Forgetting in Large Language Models Personalization