mlsanityData to 7 Oct 2026

Virtual Personas for Language Models via an Anthology of Backstories

arXiv 2407.06576 ↗First posted 9 Jul 2024cs.CL cs.AIcited by 49

Not on the map. Why?

Abstract (arXiv)

Large language models (LLMs) are trained from vast repositories of text authored by millions of distinct authors, reflecting an enormous diversity of human traits. While these models bear the potential to be used as approximations of human subjects in behavioral studies, prior efforts have been limited in steering model responses to match individual human users. In this work, we introduce "Anthology", a method for conditioning LLMs to particular virtual personas by harnessing open-ended life narratives, which we refer to as "backstories." We show that our methodology enhances the consistency and reliability of experimental outcomes while ensuring better representation of diverse sub-populations. Across three nationally representative human surveys conducted as part of Pew Research Center's American Trends Panel (ATP), we demonstrate that Anthology achieves up to 18% improvement in matching the response distributions of human respondents and 27% improvement in consistency metrics.

Key facts. Cited by 49 papers in the map (data through 7 Oct 2026). Builds on 47 of its 84 references that are in the map. First posted on arXiv 9 Jul 2024.

Builds on

47 of 84 references.

References · 47

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  4. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  5. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  6. 2020Measuring Massive Multitask Language Understandingcited by 7,768
  7. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
  8. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
  9. 2022Scaling Instruction-Finetuned Language Modelscited by 2,997
  10. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 2,950
  11. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,906
  12. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,348
35 more
  1. 2024Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preferencecited by 1,151
  2. 2022Discovering Language Model Behaviors with Model-Written Evaluationscited by 805
  3. 2023Whose Opinions Do Language Models Reflect?cited by 759
  4. 2022Out of One, Many: Using Language Models to Simulate Human Samplescited by 737
  5. 2022Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studiescited by 506
  6. 2023Large Language Models Are Not Robust Multiple Choice Selectorscited by 454
  7. 2023Is ChatGPT a Good NLG Evaluator? A Preliminary Studycited by 420
  8. 2022Using cognitive psychology to understand GPT-3cited by 389
  9. 2022Social Simulacra: Creating Populated Prototypes for Social Computing Systemscited by 300
  10. 2023Large Language Models Sensitivity to The Order of Options in Multiple-Choice Questionscited by 249
  11. 2023Can Large Language Models Transform Computational Social Science?cited by 245
  12. 2023PersonaLLM: Investigating the Ability of Large Language Models to Express Personality Traitscited by 229
  13. 2023An Overview of Catastrophic AI Riskscited by 214
  14. 2022Re3: Generating Longer Stories With Recursive Reprompting and Revisioncited by 193
  15. 2024Foundational Challenges in Assuring Alignment and Safety of Large Language Modelscited by 193
  16. 2023The political ideology of conversational AI: Converging evidence on ChatGPT's pro-environmental, left-libertarian orientationcited by 183
  17. 2023Do LLMs exhibit human-like response biases? A case study in survey designcited by 176
  18. 2023Personality Traits in Large Language Modelscited by 166
  19. 2024Quantifying the Persona Effect in LLM Simulationscited by 164
  20. 2023Fundamental Limitations of Alignment in Large Language Modelscited by 152
  21. 2023Aligning Language Models to User Opinionscited by 98
  22. 2023CoMPosT: Characterizing and Evaluating Caricature in LLM Simulationscited by 94
  23. 2022Picking on the Same Person: Does Algorithmic Monoculture lead to Outcome Homogenization?cited by 89
  24. 2023Moral Foundations of Large Language Modelscited by 84
  25. 2024Evaluating Large Language Model Biases in Persona-Steered Generationcited by 78
  26. 2022Moral Mimicry: Large Language Models Produce Moral Rationalizations Tailored to Political Identitycited by 71
  27. 2023Questioning the Survey Responses of Large Language Modelscited by 70
  28. 2022Estimating the Personality of White-Box Language Modelscited by 47
  29. 2023AI-Augmented Surveys: Leveraging Large Language Models and Surveys for Opinion Predictioncited by 46
  30. 2023Diminished Diversity-of-Thought in a Standard Large Language Modelcited by 43
  31. 2022CommunityLM: Probing Partisan Worldviews from Language Modelscited by 36
  32. 2023Language Models Trained on Media Diets Can Predict Public Opinioncited by 30
  33. 2019Earlier Isn't Always Better: Sub-aspect Analysis on Corpus and System Biases in Summarizationcited by 28
  34. 2024AnthroScore: A Computational Linguistic Measure of Anthropomorphismcited by 27
  35. 2024Eliciting Personality Traits in Large Language Modelscited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 27; 2026: 20.

49 papers.

Sort:

By area:

  1. 2025LLM Social Simulations Are a Promising Research Methodcited by 97
  2. 2025Language Model Fine-Tuning on Scaled Survey Data for Predicting Distributions of Public Opinionscited by 64
  3. 2025The Prompt Makes the Person(a): A Systematic Evaluation of Sociodemographic Persona Prompting for Large Language Modelscited by 40
  4. 2025Know You First and Be You Better: Modeling Human-Like User Simulators via Implicit Profilescited by 38
  5. 2025Finetuning LLMs for Human Behavior Prediction in Social Science Experimentscited by 35
  6. 2024Can Language Models Reason about Individualistic Human Values and Preferences?cited by 34
  7. 2025LoRe: Personalizing LLMs via Low-Rank Reward Modelingcited by 34
  8. 2026This human study did not involve human subjects: Validating LLM simulations as behavioral evidencecited by 26
  9. 2025Enhancing Personalized Multi-Turn Dialogue with Curiosity Rewardcited by 25
  10. 2025Towards a Design Guideline for RPA Evaluation: A Survey of Large Language Model-Based Role-Playing Agentscited by 22
  11. 2025Enough Coin Flips Can Make LLMs Act Bayesiancited by 19
  12. 2025User Simulation in the Era of Generative AI: User Modeling, Synthetic Data Generation, and System Evaluationcited by 16
37 more
  1. 2025Improving Language Model Personas via Rationalization with Psychological Scaffoldscited by 9
  2. 2024Rediscovering the Latent Dimensions of Personality with Large Language Models as Trait Descriptorscited by 6
  3. 2025Large Language Models as Psychological Simulators: A Methodological Guidecited by 6
  4. 2025VirtualXAI: A User-Centric Framework for Explainability Assessment Leveraging GPT-Generated Personascited by 5
  5. 2025Sleepless Nights, Sugary Days: Creating Synthetic Users with Health Conditions for Realistic Coaching Agent Interactionscited by 4
  6. 2025AdAEM: An Adaptively and Automated Extensible Measurement of LLMs' Value Differencecited by 4
  7. 2025Words Like Knives: Backstory-Personalized Modeling and Detection of Violent Communicationcited by 4
  8. 2025ValueSim: Generating Backstories to Model Individual Value Systemscited by 4
  9. 2025Vibe Check: Understanding the Effects of LLM-Based Conversational Agents' Personality and Alignment on User Perceptions in Goal-Oriented Taskscited by 4
  10. 2025Psychometric Personality Shaping Modulates Capabilities and Safety in Language Modelscited by 4
  11. 2026Identity, Cooperation and Framing Effects within Groups of Real and Simulated Humanscited by 4
  12. 2026The Illusion of Intervention: Your LLM-Simulated Experiment is an Observational Studycited by 4
  13. 2025ALIGN: Prompt-based Attribute Alignment for Reliable, Responsible, and Personalized LLM-based Decision-Makingcited by 2
  14. 2025AlignSurvey: A Comprehensive Benchmark for Human Preferences Alignment in Social Surveyscited by 2
  15. 2026When Can Digital Personas Reliably Approximate Human Survey Findings?cited by 2
  16. 2026How Well Do Large Language Models Capture Human Personality?cited by 2
  17. 2025Large Language Models Can Be a Viable Substitute for Expert Political Surveys When a Shock Disrupts Traditional Measurement Approachescited by 1
  18. 2025Synthia: Scalable Grounded Persona Generation from Social Media Datacited by 1
  19. 2025IROTE: Human-like Traits Elicitation of Large Language Model via In-Context Self-Reflective Optimizationcited by 1
  20. 2025HumAIne-Chatbot: Real-Time Personalized Conversational AI via Reinforcement Learningcited by 1
  21. 2025PrimeX: A Dataset of Worldview, Opinion, and Explanationcited by 1
  22. 2025Graph-Based Alternatives to LLMs for Human Simulationcited by 1
  23. 2026Belief-Sim: Towards Belief-Driven Simulation of Demographic Misinformation Susceptibilitycited by 1
  24. 2026Distribution-First Population Simulation: Collapse, Calibration, and Recall in Non-WEIRD LLM Persona Modelingcited by 1
  25. 2026Validated Hypotheses as a Lens for Human-Likeness Evaluation in AI Agentscited by 0
  26. 2026Fund2Persona: A Framework for Building and Refining Financial Advisor Personas from Fund Disclosure Datacited by 0
  27. 2026Anamnesis: An Open-Source Platform for Large-Scale Backstory-Conditioned Survey Simulationcited by 0
  28. 2026MemoryForge: Synthesize Lifelong Memory for Human-Like LLM Agentscited by 0
  29. 2026Emulate or Estimate? The Divergent Strengths of Base and Post-Trained Language Models for Opinion Simulationcited by 0
  30. 2026Beyond "I Can't Help With That": How Child Safety Experts Evaluate AI Chatbot Safetycited by 0
  31. 2026ExpertIVS: Sociological Expert Driven Individual Value Simulation in Large Language Modelscited by 0
  32. 2026Investigating Assistant Bias in LLM User Simulators Using a Role Vectorcited by 0
  33. 2026PTCG: Persona-guided Tree-based Counterargument Generationcited by 0
  34. 2026Pretrained Persona Mixture Models and Tandem Models for Human Simulationcited by 0
  35. 2026Understanding Reliability in LLM-based Human Behavior Simulationcited by 0
  36. 2026How Far Do Persona Effects Generalize in Language Models?cited by 0
  37. 2026Demographic Pluralism: Inference-Time Modeling of Pluralistic Human Preference Distributionscited by 0