mlsanityData to 7 Oct 2026

Aligning Language Models to User Opinions

arXiv 2305.14929 ↗First posted 24 May 2023cs.CLcited by 98

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

Abstract (arXiv)

An important aspect of developing LLMs that interact with humans is to align models' behavior to their users. It is possible to prompt an LLM into behaving as a certain persona, especially a user group or ideological persona the model captured during its pertaining stage. But, how to best align an LLM with a specific user and not a demographic or ideological group remains an open question. Mining public opinion surveys (by Pew Research), we find that the opinions of a user and their demographics and ideologies are not mutual predictors. We use this insight to align LLMs by modeling both user opinions as well as user demographics and ideology, achieving up to 7 points accuracy gains in predicting public opinions from survey questions across a broad set of topics. In addition to the typical approach of prompting LLMs with demographics and ideology, we discover that utilizing the most relevant past opinions from individual users enables the model to predict user opinions more accurately.

Key facts. Cited by 98 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 11 of its 32 references that are in the map. First posted on arXiv 24 May 2023.

Builds on

11 of 32 references.

References · 11

  1. 2017Neural Collaborative Filteringcited by 1,108
  2. 2019Generalization through Memorization: Nearest Neighbor Language Modelscited by 788
  3. 2023Whose Opinions Do Language Models Reflect?cited by 759
  4. 2023LaMP: When Large Language Models Meet Personalizationcited by 425
  5. 2023Toxicity in ChatGPT: Analyzing Persona-assigned Language Modelscited by 356
  6. 2023Chat-REC: Towards Interactive and Explainable LLMs-Augmented Recommender Systemcited by 241
  7. 2019Generating Personalized Recipes from Historical User Preferencescited by 52
  8. 2023Language Models Trained on Media Diets Can Predict Public Opinioncited by 30
  9. 2016Echo Chambers: Emotional Contagion and Group Polarization on Facebookcited by 27
  10. 2019Improving Question Answering with External Knowledgecited by 16
  11. 2021Self-Supervised Bot Play for Conversational Recommendation with Justificationscited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 7; 2024: 31; 2025: 36; 2026: 24.

98 papers.

Sort:

By area:

  1. 2024A Roadmap to Pluralistic Alignmentcited by 175
  2. 2024Towards Measuring and Modeling "Culture" in LLMs: A Surveycited by 166
  3. 2024A Comprehensive Study of Knowledge Editing for Large Language Modelscited by 157
  4. 2023Simulating Opinion Dynamics with Networks of LLM-based Agentscited by 153
  5. 2024Personalized Language Modeling from Personalized Human Feedbackcited by 124
  6. 2023Sensitivity, Performance, Robustness: Deconstructing the Effect of Sociodemographic Promptingcited by 80
  7. 2024Evaluating Large Language Model Biases in Persona-Steered Generationcited by 78
  8. 2024PERSONA: A Reproducible Testbed for Pluralistic Alignmentcited by 71
  9. 2025Language Model Fine-Tuning on Scaled Survey Data for Predicting Distributions of Public Opinionscited by 64
  10. 2023Group Preference Optimization: Few-Shot Alignment of Large Language Modelscited by 61
  11. 2024PAD: Personalized Alignment of LLMs at Decoding-Timecited by 58
  12. 2024PersonalLLM: Tailoring LLMs to Individual Preferencescited by 56
38 more
  1. 2023On the steerability of large language models toward data-driven personascited by 53
  2. 2024Virtual Personas for Language Models via an Anthology of Backstoriescited by 49
  3. 2024Random Silicon Sampling: Simulating Human Sub-Population Opinion Using a Large Language Model Based on Group-Level Demographic Informationcited by 48
  4. 2024Persona-DB: Efficient Large Language Model Personalization for Response Prediction with Collaborative Data Refinementcited by 47
  5. 2024RLHF Can Speak Many Languages: Unlocking Multilingual Preference Optimization for LLMscited by 42
  6. 2025The Prompt Makes the Person(a): A Systematic Evaluation of Sociodemographic Persona Prompting for Large Language Modelscited by 40
  7. 2023Sociodemographic Prompting is Not Yet an Effective Approach for Simulating Subjective Judgments with LLMscited by 36
  8. 2024Evaluating Cultural Adaptability of a Large Language Model via Simulation of Synthetic Personascited by 36
  9. 2023CoQuest: Exploring Research Question Co-Creation with an LLM-based Agentcited by 34
  10. 2025ChatBench: From Static Benchmarks to Human-AI Evaluationcited by 31
  11. 2026HumanLM: Simulating Users with State Alignment Beats Response Imitationcited by 31
  12. 2024Few-shot Personalization of LLMs with Mis-aligned Responsescited by 30
  13. 2025Value Profiles for Encoding Human Variationcited by 29
  14. 2024Culturally Aware and Adapted NLP: A Taxonomy and a Survey of the State of the Artcited by 26
  15. 2025SynthesizeMe! Inducing Persona-Guided Prompts for Personalized Reward Models in LLMscited by 26
  16. 2024Cultural Conditioning or Placebo? On the Effectiveness of Socio-Demographic Promptingcited by 22
  17. 2024The Potential and Challenges of Evaluating Attitudes, Opinions, and Values in Large Language Modelscited by 19
  18. 2024Self-Alignment: Improving Alignment of Cultural Values in LLMs via In-Context Learningcited by 18
  19. 2024Mitigating Hallucination in Fictional Character Role-Playcited by 17
  20. 2025Whose Boat Does it Float? Improving Personalization in Preference Tuning via Inferred User Personascited by 17
  21. 2024Position: Towards Bidirectional Human-AI Alignmentcited by 15
  22. 2024Algorithmic Fidelity of Large Language Models in Generating Synthetic German Public Opinions: A Case Studycited by 14
  23. 2024Language Models are Alignable Decision-Makers: Dataset and Application to the Medical Triage Domaincited by 13
  24. 2025Drift: Decoding-time Personalized Alignments with Implicit User Preferencescited by 13
  25. 2024Contextualized Evaluations: Judging Language Model Responses to Underspecified Queriescited by 12
  26. 2025Pairwise Calibrated Rewards for Pluralistic Alignmentcited by 12
  27. 2025Personalized LLM Decoding via Contrasting Personal Preferencecited by 12
  28. 2025Persona-judge: Personalized Alignment of Large Language Models via Token-level Self-judgmentcited by 11
  29. 2025Embedding-to-Prefix: Parameter-Efficient Personalization for Pre-Trained Large Language Modelscited by 10
  30. 2023Can Large Language Models Capture Public Opinion about Global Warming? An Empirical Assessment of Algorithmic Fidelity and Biascited by 9
  31. 2024Voices in a Crowd: Searching for Clusters of Unique Perspectivescited by 9
  32. 2025When Personalization Meets Reality: A Multi-Faceted Analysis of Personalized Preference Learningcited by 9
  33. 2025Improving Language Model Personas via Rationalization with Psychological Scaffoldscited by 9
  34. 2025Robust Multi-Objective Controlled Decoding of Large Language Modelscited by 8
  35. 2025Spotting Out-of-Character Behavior: Atomic-Level Evaluation of Persona Fidelity in Open-Ended Generationcited by 8
  36. 2024Re-examining Sexism and Misogyny Classification with Annotator Attitudescited by 7
  37. 2025HyPerAlign: Interpretable Personalized LLM Alignment via Hypothesis Generationcited by 6
  38. 2024Revealing Fine-Grained Values and Opinions in Large Language Modelscited by 5

50 most cited of 98 All 98 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Aligning LLMs with Individual Preferences via Interaction
  2. 2025On the Alignment of Large Language Models with Global Human Opinion
  3. 2025Users as Annotators: LLM Preference Learning from Comparison Mode
  4. 2025Synthesizing Public Opinions with LLMs: Role Creation, Impacts, and the Future to eDemorcacy
  5. 2024Dissecting Human and LLM Preferences
  6. 2026Reasoning Boosts Opinion Alignment in LLMs
  7. 2024Aligning to Thousands of Preferences via System Message Generalization
  8. 2025Do LLMs Align Human Values Regarding Social Biases? Judging and Explaining Social Biases with LLMs