mlsanityData to 14 Oct 2026

On the steerability of large language models toward data-driven personas

arXiv 2311.04978 ↗First posted 8 Nov 2023cs.CLcited by 53

Not on the map. Why?

Abstract (arXiv)

Large language models (LLMs) are known to generate biased responses where the opinions of certain groups and populations are underrepresented. Here, we present a novel approach to achieve controllable generation of specific viewpoints using LLMs, that can be leveraged to produce multiple perspectives and to reflect the diverse opinions. Moving beyond the traditional reliance on demographics like age, gender, or party affiliation, we introduce a data-driven notion of persona grounded in collaborative filtering, which is defined as either a single individual or a cohort of individuals manifesting similar views across specific inquiries. As individuals in the same demographic group may have different personas, our data-driven persona definition allows for a more nuanced understanding of different (latent) social groups present in the population. In addition to this, we also explore an efficient method to steer LLMs toward the personas that we define. We show that our data-driven personas significantly enhance model steerability, with improvements of between 57%-77% over our best performing baselines.

Key facts. Cited by 53 papers in the map (data through 14 Oct 2026). Builds on 25 of its 33 references that are in the map. First posted on arXiv 8 Nov 2023.

Builds on

25 of 33 references.

References · 25

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2022Training language models to follow instructions with human feedbackcited by 15,971
  3. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  4. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  5. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,915
  6. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,795
  7. 2022Large Language Models Encode Clinical Knowledgecited by 1,830
  8. 2020LightGCN: Simplifying and Powering Graph Convolution Network for Recommendationcited by 1,139
  9. 2023BloombergGPT: A Large Language Model for Financecited by 939
  10. 2022Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learningcited by 896
  11. 2023LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attentioncited by 781
  12. 2023Whose Opinions Do Language Models Reflect?cited by 773
13 more
  1. 2022Out of One, Many: Using Language Models to Simulate Human Samplescited by 752
  2. 2019Fast Transformer Decoding: One Write-Head is All You Needcited by 717
  3. 2021GPT Understands, Toocited by 716
  4. 2023Towards Measuring the Representation of Subjective Global Opinions in Language Modelscited by 437
  5. 2023Toxicity in ChatGPT: Analyzing Persona-assigned Language Modelscited by 360
  6. 2023From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Modelscited by 260
  7. 2023Evaluating the Moral Beliefs Encoded in LLMscited by 215
  8. 2023In-Context Impersonation Reveals Large Language Models' Strengths and Biasescited by 155
  9. 2023Aligning Language Models to User Opinionscited by 99
  10. 2023NLPositionality: Characterizing Design Biases of Datasets and Modelscited by 94
  11. 2022Moral Mimicry: Large Language Models Produce Moral Rationalizations Tailored to Political Identitycited by 74
  12. 2023Controlling the Extraction of Memorized Data from Large Language Models via Prompt-Tuningcited by 40
  13. 2022CommunityLM: Probing Partisan Worldviews from Language Modelscited by 36

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 14; 2025: 28; 2026: 11.

53 papers.

Sort:

By area:

  1. 2024Scaling Synthetic Data Creation with 1,000,000,000 Personascited by 417
  2. 2024From Persona to Personalization: A Survey on Role-Playing Language Agentscited by 212
  3. 2024A Roadmap to Pluralistic Alignmentcited by 184
  4. 2025ELEPHANT: Measuring and understanding social sycophancy in LLMscited by 129
  5. 2024From Individual to Society: A Survey on Social Simulation Driven by Large Language Model-based Agentscited by 82
  6. 2025Language Model Fine-Tuning on Scaled Survey Data for Predicting Distributions of Public Opinionscited by 66
  7. 2024Persona-DB: Efficient Large Language Model Personalization for Response Prediction with Collaborative Data Refinementcited by 49
  8. 2024Inverse Constitutional AI: Compressing Preferences into Principlescited by 41
  9. 2024Few-shot Personalization of LLMs with Mis-aligned Responsescited by 32
  10. 2025Value Profiles for Encoding Human Variationcited by 29
  11. 2025SynthesizeMe! Inducing Persona-Guided Prompts for Personalized Reward Models in LLMscited by 29
  12. 2024Evaluating the Prompt Steerability of Large Language Modelscited by 27
38 more
  1. 2025Valid Survey Simulations with Limited Human Data: The Roles of Prompting, Fine-Tuning, and Rectificationcited by 18
  2. 2024Plurals: A System for Guiding LLMs Via Simulated Social Ensemblescited by 17
  3. 2025Exploring the Potential of LLMs as Personalized Assistants: Dataset, Evaluation, and Analysiscited by 17
  4. 2025Can LLM Agents Maintain a Persona in Discourse?cited by 15
  5. 2025Biased Tales: Cultural and Topic Bias in Generating Children's Storiescited by 15
  6. 2025Whose Personae? Synthetic Persona Experiments in LLM Research and Pathways to Transparencycited by 14
  7. 2024LLMs with Industrial Lens: Deciphering the Challenges and Prospects -- A Surveycited by 12
  8. 2024A Simulation System Towards Solving Societal-Scale Manipulationcited by 12
  9. 2025CLASH: Evaluating Language Models on Judging High-Stakes Dilemmas from Multiple Perspectivescited by 10
  10. 2025Robust Multi-Objective Controlled Decoding of Large Language Modelscited by 9
  11. 2025Boosting Relational Deep Learning with Pretrained Tabular Modelscited by 9
  12. 2025Improving Language Model Personas via Rationalization with Psychological Scaffoldscited by 9
  13. 2025Personalized Language Models via Privacy-Preserving Evolutionary Model Mergingcited by 8
  14. 2025STEER-BENCH: A Benchmark for Evaluating the Steerability of Large Language Modelscited by 8
  15. 2025Adaptive Elicitation of Latent Information Using Natural Languagecited by 7
  16. 2025A Course Correction in Steerability Evaluation: Revealing Miscalibration and Side Effects in LLMscited by 7
  17. 2025What's Producible May Not Be Reachable: Measuring the Steerability of Generative Modelscited by 6
  18. 2025textttBluePrint: A Social Media User Dataset for LLM Persona Evaluation and Trainingcited by 6
  19. 2026Steering at the Source: Style Modulation Heads for Robust Persona Controlcited by 5
  20. 2025Using AI for User Representation: An Analysis of 83 Persona Promptscited by 4
  21. 2024No Size Fits All: The Perils and Pitfalls of Leveraging LLMs Vary with Company Sizecited by 3
  22. 2025Are Economists Always More Introverted? Analyzing Consistency in Persona-Assigned LLMscited by 3
  23. 2026AI Agents Alone Are Not (Yet) Sufficient for Social Simulationcited by 3
  24. 2025Identifying Cooperative Personalities in Multi-agent Contexts through Personality Steering with Representation Engineeringcited by 2
  25. 2025Generating Synthetic Oracle Datasets to Analyze Noise Impact: A Study on Building Function Classification Using Tweetscited by 2
  26. 2025Simulating Identity, Propagating Bias: Abstraction and Stereotypes in LLM-Generated Textcited by 2
  27. 2026Steer Model beyond Assistant: Controlling System Prompt Strength via Contrastive Decodingcited by 2
  28. 2026Say It My Way: Exploring Control in Conversational Visual Question Answering with Blind Userscited by 2
  29. 2025Is Active Persona Inference Necessary for Aligning Small Models to Personal Preferences?cited by 1
  30. 2026The Pragmatic Persona: Discovering LLM Persona through Bridging Inferencecited by 1
  31. 2024Agentic Society: Merging skeleton from real world and texture from Large Language Modelcited by 0
  32. 2024Value-Spectrum: Quantifying Preferences of Vision-Language Models via Value Decomposition in Social Media Contextscited by 0
  33. 2025Batch Aggregation: An Approach to Enhance Text Classification with Correlated Augmented Datacited by 0
  34. 2025Dynamic Evaluation Framework for Personalized and Trustworthy Agents: A Multi-Session Approach to Preference Adaptabilitycited by 0
  35. 2025Community-Aligned Behavior Under Uncertainty: Evidence of Epistemic Stance Transfer in LLMscited by 0
  36. 2026CHORUS: An Agentic Framework for Generating Realistic Deliberation Datacited by 0
  37. 2026Alignment has a Fantasia Problemcited by 0
  38. 2026The Granularity Axis: A Micro-to-Macro Latent Direction for Social Roles in Language Modelscited by 0

50 most cited of 53 All 53 (JSON)