mlsanityData to 7 Oct 2026

Improving the Distributional Alignment of LLMs using Supervision

arXiv 2507.00439 ↗First posted 1 Jul 2025cs.CLcited by 2

Not on the map. Why?

Abstract (arXiv)

The ability to accurately align LLMs with diverse population groups on subjective questions would have great value. In this work, we show that adding simple supervision can more consistently improve the alignment of LLM-generated distributions with diverse population groups, as measured across three datasets spanning public health, public opinion, and values and beliefs. Beyond evaluating average alignment, we also report how alignment varies across specific groups. Our broad findings provide insights into the distributional alignment of LLM generations with diverse populations. By conducting evaluation over many LLMs and prompting strategies, we provide a benchmark to stimulate future research.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 47 of its 83 references that are in the map. First posted on arXiv 1 Jul 2025.

Builds on

47 of 83 references.

References · 47

  1. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  2. 2023Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMscited by 946
  3. 2020StereoSet: Measuring stereotypical bias in pretrained language modelscited by 911
  4. 2023Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedbackcited by 788
  5. 2023Whose Opinions Do Language Models Reflect?cited by 759
  6. 2022Out of One, Many: Using Language Models to Simulate Human Samplescited by 737
  7. 2022Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studiescited by 506
  8. 2023Large Language Models Are Zero-Shot Time Series Forecasterscited by 491
  9. 2023Towards Measuring the Representation of Subjective Global Opinions in Language Modelscited by 424
  10. 2023SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agentscited by 350
  11. 2021Annotators with Attitudes: How Annotator Beliefs And Identities Bias Toxic Language Detectioncited by 258
  12. 2023A Survey of Confidence Estimation and Calibration in Large Language Modelscited by 253
35 more
  1. 2023Marked Personas: Using Natural Language Prompts to Measure Stereotypes in Language Modelscited by 204
  2. 2023Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMscited by 191
  3. 2024Quantifying the Persona Effect in LLM Simulationscited by 164
  4. 2024Investigating Cultural Alignment of Large Language Modelscited by 140
  5. 2024Large language models that replace human participants can harmfully misportray and flatten identity groupscited by 137
  6. 2023Cultural Alignment in Large Language Models: An Explanatory Analysis Based on Hofstede's Cultural Dimensionscited by 111
  7. 2024Modular Pluralism: Pluralistic Alignment via Multi-LLM Collaborationcited by 111
  8. 2024Can LLM be a Personalized Judge?cited by 99
  9. 2023Aligning Language Models to User Opinionscited by 98
  10. 2023CoMPosT: Characterizing and Evaluating Caricature in LLM Simulationscited by 94
  11. 2023Sensitivity, Performance, Robustness: Deconstructing the Effect of Sociodemographic Promptingcited by 80
  12. 2024Benchmarking Distributional Alignment of Large Language Modelscited by 58
  13. 2024From Words to Numbers: Your Large Language Model Is Secretly A Capable Regressor When Given In-Context Examplescited by 55
  14. 2025Randomness, Not Representation: The Unreliability of Evaluating Cultural Alignment in LLMscited by 54
  15. 2023When Do Annotator Demographics Matter? Measuring the Influence of Annotator Demographics with the POPQUORN Datasetcited by 51
  16. 2025Specializing Large Language Models to Simulate Survey Response Distributions for Global Populationscited by 50
  17. 2024Random Silicon Sampling: Simulating Human Sub-Population Opinion Using a Large Language Model Based on Group-Level Demographic Informationcited by 48
  18. 2024Self-Alignment of Large Language Models via Monopolylogue-based Social Scene Simulationcited by 46
  19. 2023ChatGPT to Replace Crowdsourcing of Paraphrases for Intent Classification: Higher Diversity and Comparable Model Robustnesscited by 41
  20. 2023Sociodemographic Prompting is Not Yet an Effective Approach for Simulating Subjective Judgments with LLMscited by 36
  21. 2024Evaluating Cultural Adaptability of a Large Language Model via Simulation of Synthetic Personascited by 36
  22. 2024OmniPred: Language Models as Universal Regressorscited by 34
  23. 2025THOUGHTTERMINATOR: Benchmarking, Calibrating, and Mitigating Overthinking in Reasoning Modelscited by 34
  24. 2025Beyond Demographics: Fine-tuning Large Language Models to Predict Individuals' Subjective Text Perceptionscited by 31
  25. 2024Take Caution in Using LLMs as Human Surrogates: Scylla Ex Machinacited by 29
  26. 2025Value Profiles for Encoding Human Variationcited by 29
  27. 2024What Are the Odds? Language Models Are Capable of Probabilistic Reasoningcited by 25
  28. 2024Annotation alignment: Comparing LLM and human annotations of conversational safetycited by 22
  29. 2024Cultural Conditioning or Placebo? On the Effectiveness of Socio-Demographic Promptingcited by 22
  30. 2023Aligning Large Language Models with Human Opinions through Persona Selection and Value--Belief--Norm Reasoningcited by 19
  31. 2024The Potential and Challenges of Evaluating Attitudes, Opinions, and Values in Large Language Modelscited by 19
  32. 2024Self-Alignment: Improving Alignment of Cultural Values in LLMs via In-Context Learningcited by 18
  33. 2025Can A Society of Generative Agents Simulate Human Behavior and Inform Public Health Policy? A Case Study on Vaccine Hesitancycited by 15
  34. 2025Deep Binding of Language Model Virtual Personas: a Study on Approximating Political Partisan Misperceptionscited by 9
  35. 2025Quantile Regression with Large Language Models for Price Predictioncited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026RELISH: LLM REgression with a Latent Iterative State Headcited by 1
  2. 2026When Can LLM Digital Twins Reduce Human Measurement? From Behavioral Fidelity to Statistical Substitutabilitycited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Controlling Distributional Bias in Multi-Round LLM Generation via KL-Optimized Fine-Tuning
  2. 2026Beyond Marginal Distributions: A Framework to Evaluate the Representativeness of Demographic-Aligned LLMs
  3. 2026Can Persona-Prompted LLMs Emulate Subgroup Values? An Empirical Analysis of Generalisability and Fairness in Cultural Alignment
  4. 2025Group Preference Alignment: Customized LLM Response Generation from In-Situ Conversations
  5. 2025Do LLMs Align Human Values Regarding Social Biases? Judging and Explaining Social Biases with LLMs
  6. 2025The Sign Estimator: LLM Alignment in the Face of Choice Heterogeneity
  7. 2025AlignSurvey: A Comprehensive Benchmark for Human Preferences Alignment in Social Surveys
  8. 2025ALIGN: Prompt-based Attribute Alignment for Reliable, Responsible, and Personalized LLM-based Decision-Making