mlsanityData to 7 Oct 2026

The Better Angels of Machine Personality: How Personality Relates to LLM Safety

arXiv 2407.12344 ↗First posted 17 Jul 2024cs.CL cs.CYcited by 21

Not on the map. Why?

Abstract (arXiv)

Personality psychologists have analyzed the relationship between personality and safety behaviors in human society. Although Large Language Models (LLMs) demonstrate personality traits, the relationship between personality traits and safety abilities in LLMs still remains a mystery. In this paper, we discover that LLMs' personality traits are closely related to their safety abilities, i.e., toxicity, privacy, and fairness, based on the reliable MBTI-M scale. Meanwhile, the safety alignment generally increases various LLMs' Extraversion, Sensing, and Judging traits. According to such findings, we can edit LLMs' personality traits and improve their safety performance, e.g., inducing personality from ISTJ to ISTP resulted in a relative improvement of approximately 43% and 10% in privacy and fairness performance, respectively. Additionally, we find that LLMs with different personality traits are differentially susceptible to jailbreak. This study pioneers the investigation of LLM safety from a personality perspective, providing new insights into LLM safety enhancement.

Key facts. Cited by 21 papers in the map (data through 7 Oct 2026). Builds on 55 of its 107 references that are in the map. First posted on arXiv 17 Jul 2024.

Builds on

55 of 107 references.

References · 55

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  3. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  4. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,634
  5. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,317
  6. 2019Fine-Tuning Language Models from Human Preferencescited by 2,124
  7. 2023Jailbroken: How Does LLM Safety Training Fail?cited by 1,565
  8. 2023Inference-Time Intervention: Eliciting Truthful Answers from a Language Modelcited by 1,259
  9. 2023Representation Engineering: A Top-Down Approach to AI Transparencycited by 1,239
  10. 2023Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!cited by 1,106
  11. 2023Large Language Models are not Fair Evaluatorscited by 1,050
  12. 2021A General Language Assistant as a Laboratory for Alignmentcited by 1,023
38 more
  1. 2016The LAMBADA dataset: Word prediction requiring a broad discourse contextcited by 960
  2. 2020StereoSet: Measuring stereotypical bias in pretrained language modelscited by 911
  3. 2023Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formattingcited by 778
  4. 2023RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedbackcited by 615
  5. 2016Inherent Trade-Offs in the Fair Determination of Risk Scorescited by 582
  6. 2023DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Modelscited by 505
  7. 2023GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Ciphercited by 401
  8. 2023Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignmentcited by 394
  9. 2023Toxicity in ChatGPT: Analyzing Persona-assigned Language Modelscited by 356
  10. 2023Character-LLM: A Trainable Agent for Role-Playingcited by 335
  11. 2019Differential Privacy Has Disparate Impact on Model Accuracycited by 316
  12. 2023Shadow Alignment: The Ease of Subverting Safely-Aligned Language Modelscited by 284
  13. 2024TrustLLM: Trustworthiness in Large Language Modelscited by 280
  14. 2023AI Alignment: A Comprehensive Surveycited by 256
  15. 2023Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theorycited by 218
  16. 2020To be Robust or to be Fair: Towards Fairness in Adversarial Trainingcited by 137
  17. 2019Privacy Risks of Securing Machine Learning Models against Adversarial Examplescited by 136
  18. 2022Evaluating and Inducing Personality in Pre-trained Language Modelscited by 122
  19. 2021Trustworthy AI: A Computational Perspectivecited by 93
  20. 2024Can multiple-choice questions really be useful in detecting the abilities of LLMs?cited by 66
  21. 2024CodeChameleon: Personalized Encryption Framework for Jailbreaking Large Language Modelscited by 65
  22. 2023CharacterChat: Learning towards Conversational AI with Personalized Social Supportcited by 58
  23. 2024EasyJailbreak: A Unified Framework for Jailbreaking Large Language Modelscited by 57
  24. 2023Do LLMs Possess a Personality? Making the MBTI Test an Amazing Evaluation for Large Language Modelscited by 54
  25. 2023Have Large Language Models Developed a Personality?: Applicability of Self-Assessment Tests in Measuring Personality in LLMscited by 32
  26. 2023Exploring the Sensitivity of LLMs' Decision-Making Capabilities: Insights from Prompt Variation and Hyperparameterscited by 32
  27. 2022Learning to Model Editing Processescited by 30
  28. 2023Who is ChatGPT? Benchmarking LLMs' Psychological Portrayal Using PsychoBenchcited by 28
  29. 2023Trojan Activation Attack: Red-Teaming Large Language Models using Activation Steering for Safety-Alignmentcited by 27
  30. 2023An Empirical Study of Metrics to Measure Representational Harms in Pre-Trained Language Modelscited by 24
  31. 2022Differential Privacy has Bounded Impact on Fairness in Classificationcited by 18
  32. 2023An evolutionary model of personality traits related to cooperative behavior using a large language modelcited by 18
  33. 2024Towards Tracing Trustworthiness Dynamics: Revisiting Pre-training Period of Large Language Modelscited by 18
  34. 2023Revisiting the Reliability of Psychological Scales on Large Language Modelscited by 16
  35. 2024PHAnToM: Persona-based Prompting Has An Effect on Theory-of-Mind Reasoning in Large Language Modelscited by 16
  36. 2024ControlLM: Crafting Diverse Personalities for Language Modelscited by 15
  37. 2024Identifying Multiple Personalities in Large Language Models with External Evaluationcited by 10
  38. 2023Machine Mindset: An MBTI Exploration of Large Language Modelscited by 9

50 most cited of 55 All 55 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 11; 2026: 6.

21 papers.

Sort:

By area:

  1. 2024Programming Refusal with Conditional Activation Steeringcited by 191
  2. 2024Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Surveycited by 52
  3. 2025Visual Contextual Attack: Jailbreaking MLLMs with Image-Driven Context Injectioncited by 23
  4. 2025EmoAgent: Assessing and Safeguarding Human-AI Interaction for Mental Health Safetycited by 21
  5. 2025X-Boundary: Establishing Exact Safety Boundary to Shield LLMs from Multi-Turn Jailbreaks without Compromising Usabilitycited by 20
  6. 2024From Imitation to Introspection: Probing Self-Consciousness in Language Modelscited by 14
  7. 2025Exploring the Impact of Personality Traits on LLM Bias and Toxicitycited by 14
  8. 2025Enhancing Jailbreak Attacks on LLMs via Persona Promptscited by 10
  9. 2025Bullying the Machine: How Personas Increase LLM Vulnerabilitycited by 8
  10. 2026Generative AI collective behavior needs an interactionist paradigmcited by 6
  11. 2025Personality as a Probe for LLM Evaluation: Method Trade-offs and Downstream Effectscited by 4
  12. 2025Identifying Cooperative Personalities in Multi-agent Contexts through Personality Steering with Representation Engineeringcited by 2
9 more
  1. 2025Integrating Personality into Digital Humans: A Review of LLM-Driven Approaches for Virtual Realitycited by 2
  2. 2026Structured Personality Control and Adaptation for LLM Agentscited by 1
  3. 2026Funny or Persuasive, but Not Both: Evaluating Fine-Grained Multi-Concept Control in LLMscited by 1
  4. 2024A Novel Psychometrics-Based Approach to Developing Professional Competency Benchmark for Large Language Modelscited by 0
  5. 2025Human-Centric Community Detection in Hybrid Metaverse Networks with Integrated AI Entitiescited by 0
  6. 2025MindShift: Analyzing Language Models' Reactions to Psychological Promptscited by 0
  7. 2026Modeling Complex Behaviors: Multi-Personality Composition and Dynamic Switching in Vision-Language Modelscited by 0
  8. 2026From Representations to Behaviors: Exploring the Person-Situation-Behavior Triad in LLMscited by 0
  9. 2026The Fragility of Jailbreak Robustness Across Operational Statescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025The Personality Illusion: Revealing Dissociation Between Self-Reports & Behavior in LLMs
  2. 2026Making Your LLMs More Objective: Stabilizing LLM Safety Behavior Across Traits with Trait-Invariant Safety Tuning
  3. 2026Can LLMs Infer Conversational Agent Users' Personality Traits from Chat History?
  4. 2022Evaluating Psychological Safety of Large Language Models
  5. 2025Humanizing LLMs: A Survey of Psychological Measurements with Tools, Datasets, and Human-Agent Applications
  6. 2026Personality as Relational Infrastructure: User Perceptions of Personality-Trait-Infused LLM Messaging
  7. 2025Beyond BFI: The CSI for Enhanced Reliability and Validity in Evaluating LLM Personality Traits
  8. 2025Activation-Space Personality Steering: Hybrid Layer Selection for Stable Trait Control in LLMs