mlsanityData to 7 Oct 2026

Personality Alignment of Large Language Models

arXiv 2408.11779 ↗First posted 21 Aug 2024cs.CLcited by 36

On the map: LLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment

Abstract (arXiv)

Aligning large language models (LLMs) typically aim to reflect general human values and behaviors, but they often fail to capture the unique characteristics and preferences of individual users. To address this gap, we introduce the concept of Personality Alignment. This approach tailors LLMs' responses and decisions to match the specific preferences of individual users or closely related groups. Inspired by psychometrics, we created the Personality Alignment with Personality Inventories (PAPI) dataset, which includes data from over 320,000 real subjects across multiple personality assessments, including both the Big Five Personality Factors and Dark Triad traits. This comprehensive dataset enables quantitative evaluation of LLMs' alignment capabilities across both positive and potentially problematic personality dimensions. Recognizing the challenges of personality alignments, such as limited personal data, diverse preferences, and scalability requirements, we developed an activation intervention optimization method. This method enhances LLMs' ability to efficiently align with individual behavioral preferences using minimal data and computational resources. Remarkably, our method, PAS, achieves superior performance while requiring only 1/5 of the optimization time compared to DPO, offering practical value for personality alignment. Our work paves the way for future AI systems to make decisions and reason in truly personality ways, enhancing the relevance and meaning of AI interactions for each user and advancing human-centered artificial intelligence. The dataset and code are released at https://github.com/zhu-minjun/PAlign.

Key facts. Cited by 36 papers in the map (data through 7 Oct 2026). Placed in Human values and AI feedback alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation. Builds on 69 of its 114 references that are in the map. First posted on arXiv 21 Aug 2024.

Builds on

69 of 114 references.

Closest ancestors · 5

Same direction, newest first

  1. 2024Personalized Language Modeling from Personalized Human Feedback6 Feb
  2. 2023Compositional preference models for aligning LMs17 Oct
  3. 2023Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging17 Oct
  4. 2023Bridging the Gap: A Survey on Integrating (Human) Feedback for Natural Language Generation1 May
  5. 2022Constitutional AI: Harmlessness from AI Feedback15 Dec

Other references · 64

  1. 2017Attention Is All You Needcited by 59,932
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2017Proximal Policy Optimization Algorithmscited by 14,441
  4. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  5. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  6. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  7. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  8. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  9. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,769
  10. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,634
  11. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,355
  12. 2023Qwen Technical Reportcited by 3,273
38 more
  1. 2022Locating and Editing Factual Associations in GPTcited by 2,609
  2. 2022Emergent Abilities of Large Language Modelscited by 2,483
  3. 2019HuggingFace's Transformers: State-of-the-art Natural Language Processingcited by 2,201
  4. 2018CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledgecited by 1,793
  5. 2022Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Themcited by 1,767
  6. 2023Inference-Time Intervention: Eliciting Truthful Answers from a Language Modelcited by 1,259
  7. 2023Steering Llama 2 via Contrastive Activation Additioncited by 1,009
  8. 2023A General Theoretical Paradigm to Understand Learning from Human Preferencescited by 906
  9. 2024Gemma: Open Models Based on Gemini Research and Technologycited by 889
  10. 2021Are NLP Models really able to Solve Simple Math Word Problems?cited by 861
  11. 2022Discovering Latent Knowledge in Language Models Without Supervisioncited by 733
  12. 2023RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignmentcited by 672
  13. 2023Safe RLHF: Safe Reinforcement Learning from Human Feedbackcited by 630
  14. 2023The Falcon Series of Open Language Modelscited by 526
  15. 2023Dissecting Recall of Factual Associations in Auto-Regressive Language Modelscited by 512
  16. 2022Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studiescited by 506
  17. 2019Release Strategies and the Social Impacts of Language Modelscited by 505
  18. 2023Towards Measuring the Representation of Subjective Global Opinions in Language Modelscited by 424
  19. 2016Solving General Arithmetic Word Problemscited by 353
  20. 2022Large Language Models are Better Reasoners with Self-Verificationcited by 304
  21. 2023AI Alignment: A Comprehensive Surveycited by 256
  22. 2023The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learningcited by 251
  23. 2019Risks from Learned Optimization in Advanced Machine Learning Systemscited by 250
  24. 2023Large Language Model Alignment: A Surveycited by 241
  25. 2023An Overview of Catastrophic AI Riskscited by 214
  26. 2023Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMscited by 191
  27. 2023Localizing Model Behavior with Path Patchingcited by 182
  28. 2023InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviewscited by 177
  29. 2023RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Modelscited by 173
  30. 2024Arithmetic Control of LLMs for Diverse User Preferences: Directional Preference Alignment with Multi-Objective Rewardscited by 145
  31. 2024A Minimaximalist Approach to Reinforcement Learning from Human Feedbackcited by 141
  32. 2018Parametric Noise Injection: Trainable Randomness to Improve Deep Neural Network Robustness against Adversarial Attackcited by 123
  33. 2022Evaluating and Inducing Personality in Pre-trained Language Modelscited by 122
  34. 2024On Prompt-Driven Safeguarding for Large Language Modelscited by 109
  35. 2023Interpretability at Scale: Identifying Causal Mechanisms in Alpacacited by 102
  36. 2024Decoding-Time Language Model Alignment with Multiple Objectivescited by 90
  37. 2024Decoding-time Realignment of Language Modelscited by 67
  38. 2024HYDRA: Model Factorization Framework for Black-Box LLM Personalizationcited by 59

50 most cited of 64 All 64 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 20; 2026: 13.

36 papers.

Sort:

By area:

  1. 2025The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoningcited by 160
  2. 2025DeepScientist: Advancing Frontier-Pushing Scientific Findings Progressivelycited by 56
  3. 2025The Personality Illusion: Revealing Dissociation Between Self-Reports & Behavior in LLMscited by 35
  4. 2024Can Language Models Reason about Individualistic Human Values and Preferences?cited by 34
  5. 2025LoRe: Personalizing LLMs via Low-Rank Reward Modelingcited by 34
  6. 2024Locking Down the Finetuned LLMs Safetycited by 22
  7. 2025Open Character Training: Shaping the Persona of AI Assistants through Constitutional AIcited by 19
  8. 2025Towards Personalized Deep Research: Benchmarks and Evaluationscited by 14
  9. 2026PERSONA: Dynamic and Compositional Inference-Time Personality Control via Activation Vector Algebracited by 11
  10. 2025On-the-fly Preference Alignment via Principle-Guided Decodingcited by 10
  11. 2026PersonaVLM: Long-Term Personalized Multimodal LLMscited by 10
  12. 2024Neuron-based Personality Trait Induction in Large Language Modelscited by 9
24 more
  1. 2025Bullying the Machine: How Personas Increase LLM Vulnerabilitycited by 8
  2. 2025TinyTroupe: An LLM-powered Multiagent Persona Simulation Toolkitcited by 7
  3. 2025PrefDisco: Benchmarking Proactive Personalized Reasoningcited by 7
  4. 2025T-POP: Test-Time Personalization with Online Preference Feedbackcited by 6
  5. 2025Counterfactual Reasoning for Steerable Pluralistic Value Alignment of Large Language Modelscited by 5
  6. 2026Positive Alignment: Artificial Intelligence for Human Flourishingcited by 5
  7. 2025On the Adaptive Psychological Persuasion of Large Language Modelscited by 3
  8. 2026Do Personality Traits Interfere? Geometric Limitations of Steering in Large Language Modelscited by 3
  9. 2025Integrating Personality into Digital Humans: A Review of LLM-Driven Approaches for Virtual Realitycited by 2
  10. 2025Beyond BFI: The CSI for Enhanced Reliability and Validity in Evaluating LLM Personality Traitscited by 2
  11. 2025Eliciting Chain-of-Thought in Base LLMs via Gradient-Based Representation Optimizationcited by 2
  12. 2026Enhancing Persona Following at Decoding Time via Dynamic Importance Estimation for Role-Playing Agentscited by 2
  13. 2025ValuePilot: A Two-Phase Framework for Value-Driven Decision-Makingcited by 1
  14. 2026Personalities at Play: Probing Alignment in AI Teammatescited by 1
  15. 2026Are Dilemmas and Conflicts in LLM Alignment Solvable? A View from Priority Graphcited by 1
  16. 2025Who are you, ChatGPT? Personality and Demographic Style in LLM-Generated Contentcited by 0
  17. 2025Cognitive Alignment in Personality Reasoning: Leveraging Prototype Theory for MBTI Inferencecited by 0
  18. 2025ValuePilot: A Two-Phase Framework for Value-Driven Decision-Makingcited by 0
  19. 2026After Talking with 1,000 Personas: Learning Preference-Aligned Proactive Assistants From Large-Scale Persona Interactionscited by 0
  20. 2026EpiPersona: Persona Projection and Episode Coupling for Pluralistic Preference Modelingcited by 0
  21. 2026Psychological Concept Neurons: Can Neural Control Bias Probing and Shift Generation in LLMs?cited by 0
  22. 2026DPN-LE: Dual Personality Neuron Localization and Editing for Large Language Modelscited by 0
  23. 2026Modeling Complex Behaviors: Multi-Personality Composition and Dynamic Switching in Vision-Language Modelscited by 0
  24. 2026Efficient Safety Alignment of Language Models via Latent Personality Traitscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Evaluating LLM Alignment on Personality Inference from Real-World Interview Data
  2. 2026PACIFIC: Can LLMs Discern the Psychometric Traits Influencing Your Preferences? Personality-Driven Preference Alignment in LLMs
  3. 2024Aligning LLMs with Individual Preferences via Interaction
  4. 2025Activation-Space Personality Steering: Hybrid Layer Selection for Stable Trait Control in LLMs
  5. 2025The Geometry of Persona: Disentangling Personality from Reasoning in Large Language Models
  6. 2024LLM Agents in Interaction: Measuring Personality Consistency and Linguistic Alignment in Interacting Populations of Large Language Models
  7. 2024Assessing Social Alignment: Do Personality-Prompted Large Language Models Behave Like Humans?
  8. 2025From Five Dimensions to Many: Large Language Models as Precise and Interpretable Psychological Profilers