Personalized Language Models

Follow this topic Ask about this topic

Personalized language models aim to make responses relevant to a particular user rather than relying only on general patterns learned during pretraining. Common approaches retrieve relevant records from user histories, maintain structured profiles or persistent memories, or adapt models with parameter-efficient methods such as LoRA; inference-time steering, preference ranking, and feedback-based learning offer alternatives. Benchmarks such as LaMP, LongLaMP, and PersonaMem test preference matching, memory use, and generation across users and longer interactions, while human studies examine whether personalization feels useful and appropriate. A central challenge is using personal information when it is relevant without over-applying it, compromising privacy, reinforcing bias, or weakening general response quality.

Latest papers

89 papers21 papers in the last four weeks, up 40% on the four weeks before. 0.1% of all new papers.

Recall Isn't Enough: Bounding Commitments in Personalized Language Systems
May 15, 2026Rui Tang, Yichi Zhang, Xi Chen +4Memory-Augmented Language Models Controllable Text Generation
OpenAsk · Stern School of Business, New York University · Bank of Hebei +4
Emotion-Attended Stateful Memory (EASM):The Architecture for Hyper-Personalization at Scale
May 14, 2026Vineet Kotecha, Vansh GuptaMemory-Augmented Language Models Personalized Language Models
divAIne Research
CLIPer: Tailoring Diverse User Preference via Classifier-Guided Inference-Time Personalization
May 8, 2026Jinyan Su, Jinpeng Zhou, Claire Cardie +1Language Model Steering LLM Personalization
Cornell University
Preference Heads in Large Language Models: A Mechanistic Framework for Interpretable Personalization
Apr 24, 2026Weixu Zhang, Ye Yuan, Changjiang Han +7LLM Alignment Language Model Steering
McGill University · Mila - Quebec AI Institute · MBZUAI +2
JudgeMeNot: Personalizing Large Language Models to Emulate Judicial Reasoning in Hebrew
Apr 20, 2026Itay Razumenko, Arnon Sturm, Nir GrinbergLegal NLP LLM Personalization
Computer and Information Science Ben-Gurion University of the Negev Beer-Sheva, Israel
Beyond Static Personas: Situational Personality Steering for Large Language Models
Apr 15, 2026Zesheng Wei, Mengxiang Li, Zilei Wang +1Language Model Steering Personality Modeling in Language Models
University of Science and Technology of China · Singapore Management University
TSUBASA: Improving Long-Horizon Personalization via Evolving Memory and Self-Learning with Context Distillation
Apr 9, 2026Xinliang Frederick Zhang, Lu WangPersonalized Language Models Memory-Augmented Language Models
Computer Science and Engineering, University of Michigan, Ann Arbor, MI
Persona Matters: Effects of Activation Steering on Short Answer Generation and Scoring
Apr 8, 2026Yongchao Wu, Aron HenrikssonOpen-Ended Generation Language Model Steering
Stockholm University, NOD-huset, Borgarfjordsgatan 12, 16455 Stockholm, Sweden
High-Stakes Personalization: Rethinking LLM Customization for Individual Investor Decision-Making
Apr 5, 2026Yash Ganpat SawantPersonalized Language Models Personalized Language Model Alignment
Uncertainty-Aware Variational Reward Factorization via Probabilistic Preference Bases for LLM Personalization
Apr 1, 2026Gyuseok Lee, Wonbin Kweon, Zhenrui Yue +3Personalized Language Models Personalized Language Model Alignment
University of Illinois Urbana-Champaign · Korea University
PERMA: Benchmarking Personalized Memory Agents via Event-Driven Preference and Realistic Task Environments
Mar 24, 2026Shuochen Liu, Junyi Zhu, Long Shu +11Memory Agent Benchmarks Long-Term Conversational Memory
University of Science and Technology of China · ESAT-PSI, KU Leuven · City University of Hong Kong +2
HUOZIIME: An On-Device LLM-enhanced Input Method for Deep Personalization
Mar 23, 2026Baocai Shan, Yuzhuang Xu, Wanxiang ChePersonalized Language Models On-Device Language Model Inference
Harbin Institute of Technology, Harbin, China
PersonaVLM: Long-Term Personalized Multimodal LLMs
Mar 20, 2026Chang Nie, Chaoyou Fu, Yifan Zhang +2Personalized Language Models Multimodal Agents
Nanjing University · ByteDance
BenchPreS: A Benchmark for Context-Aware Personalized Preference Selectivity of Persistent-Memory LLMs
Mar 17, 2026Sangyeon Yoon, Hyesoo Hong, Wonje Jeung +5Personalized Language Models LLM Evaluation
Yonsei University · LG AI Research
SpecSteer: Synergizing Local Context and Global Reasoning for Efficient Personalized Generation
Mar 17, 2026Hang Lv, Sheng Liang, Hao Wang +6Personalized Language Models On-Device Language Model Inference
University of Science and Technology of China · Huawei Technologies Co., Ltd.
Customizing ChatGPT for Second Language Speaking Practice: Genuine Support or Just a Marketing Gimmick?
Mar 16, 2026Fanfei MengAI in Education Personalized Language Models
University of Pennsylvania
Marked Pedagogies: Examining Linguistic Biases in Personalized Automated Writing Feedback
Mar 12, 2026Mei Tan, Lena Phalen, Dorottya DemszkyLinguistic Bias in Language Models Demographic Bias in Language Models
Stanford University, Stanford, California, USA
COACH meets QUORUM: A Framework and Pipeline for Aligning User, Expert and Developer Perspectives in LLM-generated Health Counselling
Mar 9, 2026Yee Man Ng, Bram van Dijk, Pieter Beynen +5Clinical Language Model Evaluation Medical LLMs
Leiden University · Leiden University Medical Center · Healthy Chronos
Structured Exploration vs. Generative Flexibility: A Field Study Comparing Bandit and LLM Architectures for Personalised Health Behaviour Interventions
Mar 6, 2026Dominik P. Hofer, Haochen Song, Rania Islambouli +5Personalized Language Models Contextual Bandits
Ludwig Boltzmann Institute for Digital Health and Prevention, Salzburg, Austria · University of Toronto, Toronto, Ontario, Canada · Stanford University, Stanford, California, United States of America
Addressing the Ecological Fallacy in Larger LMs with Human Context
Mar 6, 2026Nikita Soni, Dhruv Vijay Kunjadiya, Pratham Piyush Shah +3Language Modeling LLM Training
Department of Computer Science, Stony Brook University · College of Connected Computing, Vanderbilt University, USA
Individual Turing Test: A Case Study of LLM-based Simulation Using Longitudinal Personal Data
Mar 1, 2026Minghao Guo, Ziyi Ye, Wujiang Xu +3Large Language Model-Based Role-Play Simulation Personalized Language Models
Rutgers University, New Brunswick, NJ, USA · Fudan University, Shanghai, China · Microsoft, New York, NY, USA
Addressing Climate Action Misperceptions with Generative AI
Feb 26, 2026Miriam Remshard, Yara Kyrychenko, Sander van der Linden +4Persuasion in Language Models Personalized Language Models
University of Cambridge Cambridge, UK · Yale University New Haven, CT, USA · Harvard T.H. Chan School of Public Health Boston, MA, USA
Personalized Graph-Empowered Large Language Model for Proactive Information Access
Feb 25, 2026Chia Cheng Chang, An-Zi Yen, Hen-Hsen Huang +1Persistent Memory for Language Models Information Retrieval
Department of Computer Science and Information Engineering, National Taiwan University, Taipei, Taiwan · Department of Computer Science, National Yang Ming Chiao Tung University, Hsinchu, Taiwan · Institute of Information Science, Academia Sinica, Taipei, Taiwan +1
Personalized Prediction of Perceived Message Effectiveness Using Large Language Model Based Digital Twins
Feb 23, 2026Jasmin Han, Janardan Devkota, Joseph Waring +8Digital Twins Personalized Language Models
Department of Mental Health, Johns Hopkins Bloomberg School of Public Health, Baltimore, MD, USA · Department of Health Sciences, Towson University, Towson, USA · Addiction Research Group, University of East Anglia, Norwich, UK +8
Long Context, Less Focus: A Scaling Gap in LLMs Revealed through Privacy and Personalization
Feb 16, 2026Shangding GuPrivacy Leakage in Language Models Long-Context Language Model Evaluation
University of California, Berkeley
Do Implicit Personalization and Explicit Styles Conflict? PsPLUG: A Lightweight Plug-in for Balancing Personalization and Style in Customized LLMs
Jan 10, 2026Yutong Song, Jiang Wu, Shaofan Yuan +5LLM Personalization Controllable Text Generation
University of California, Irvine · Independent Researcher · TikTok
Iterative Critique-Refine Framework for Enhancing LLM Personalization
Oct 28, 2025Durga Prasad Maram, Dhruvin Gandhi, Zonghai Yao +5LLM Personalization Personalized Language Models
University of Massachusetts Amherst · Adobe Research · University of Oregon +1
POPI: Personalizing LLMs via Optimized Natural Language Preference Inference
Oct 17, 2025Yizhuo Chen, Xin Liu, Ruijie Wang +7LLM Personalization Personalized Language Models
University of Illinois Urbana-Champaign · Amazon · University of Notre Dame
FaST: Feature-aware Sampling and Tuning for Personalized Preference Alignment with Limited Data
Aug 6, 2025Thibaut Thonet, Germán Kruszewski, Jos Rozen +2LLM Personalization Personalized Language Models
1NAVER Labs Europe · 2Independent Researcher

May 15, 2026J/K move · Enter open · S save

Recall Isn't Enough: Bounding Commitments in Personalized Language Systems

Rui Tang, Yichi Zhang, Xi Chen, Chen Dong+3

OpenAsk · Stern School of Business, New York University · Bank of Hebei+4

Memory-Augmented Language Models Controllable Text Generation Personalized Language Models Language Modeling

Open paper AskPDF arXiv

Long-context and memory systems usually treat personalization as a recall problem. In practice, many failures occur later, when a system commits: it turns noisy hints into hard constraints, drops rare witnesses, forgets downstream obligations, or answers despite infeasibility. We introduce Contract-Bounded Evidence Activation (CBEA) with Lexicographic Commitment Validation (LCV). CBEA activates a bounded evidence set using typed coverage, tail witnesses, and consequence debt; LCV validates structured commitments before prose and routes infeasible states to repair, abstention, or recontract. Across 360 fixtures and three generation backends, CBEA+LCV reaches zero failures within validator scope at 0.49-0.60 availability over attempted runs. Raw and long-context baselines with the same LCV gate reach zero only at 0.003-0.092. A shadow oracle diagnostic marks the limit: CBEA+LCV recalls 0.012 of uncompiled visible facts, while raw recalls 0.53. The result is a bounded operating point: explicit commitment control and 74-75% lower median input payload, not universal memory dominance.