mlsanityData to 7 Oct 2026

The Potential and Challenges of Evaluating Attitudes, Opinions, and Values in Large Language Models

arXiv 2406.11096 ↗First posted 16 Jun 2024cs.CLcited by 19

Not on the map. Why?

Abstract (arXiv)

Recent advances in Large Language Models (LLMs) have sparked wide interest in validating and comprehending the human-like cognitive-behavioral traits LLMs may capture and convey. These cognitive-behavioral traits include typically Attitudes, Opinions, Values (AOVs). However, measuring AOVs embedded within LLMs remains opaque, and different evaluation methods may yield different results. This has led to a lack of clarity on how different studies are related to each other and how they can be interpreted. This paper aims to bridge this gap by providing a comprehensive overview of recent works on the evaluation of AOVs in LLMs. Moreover, we survey related approaches in different stages of the evaluation pipeline in these works. By doing so, we address the potential and challenges with respect to understanding the model, human-AI alignment, and downstream application in social sciences. Finally, we provide practical insights into evaluation methods, model enhancement, and interdisciplinary collaboration, thereby contributing to the evolving landscape of evaluating AOVs in LLMs.

Key facts. Cited by 19 papers in the map (data through 7 Oct 2026). Builds on 78 of its 149 references that are in the map. First posted on arXiv 16 Jun 2024.

Builds on

78 of 149 references.

References · 78

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  3. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  4. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  5. 2020Measuring Massive Multitask Language Understandingcited by 7,768
  6. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
  7. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,919
  8. 2021Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivitycited by 1,122
  9. 2022Discovering Language Model Behaviors with Model-Written Evaluationscited by 805
  10. 2023Whose Opinions Do Language Models Reflect?cited by 759
  11. 2023Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedbackcited by 743
  12. 2022Out of One, Many: Using Language Models to Simulate Human Samplescited by 737
38 more
  1. 2020Aligning AI With Shared Human Valuescited by 706
  2. 2023Large Language Models Are Not Robust Multiple Choice Selectorscited by 454
  3. 2023Towards Measuring the Representation of Subjective Global Opinions in Language Modelscited by 424
  4. 2022Using cognitive psychology to understand GPT-3cited by 389
  5. 2023Toxicity in ChatGPT: Analyzing Persona-assigned Language Modelscited by 356
  6. 2023From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Modelscited by 257
  7. 2020Social Chemistry 101: Learning to Reason about Social and Moral Normscited by 253
  8. 2023PersonaLLM: Investigating the Ability of Large Language Models to Express Personality Traitscited by 229
  9. 2023Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology Viewcited by 221
  10. 2022Neural Theory-of-Mind? On the Limits of Social Intelligence in Large LMscited by 220
  11. 2023Evaluating Large Language Models in Theory of Mind Taskscited by 217
  12. 2022Challenges and Strategies in Cross-Cultural NLPcited by 216
  13. 2023Evaluating the Moral Beliefs Encoded in LLMscited by 211
  14. 2023Marked Personas: Using Natural Language Prompts to Measure Stereotypes in Language Modelscited by 204
  15. 2023Assessing Cross-Cultural Alignment between ChatGPT and Human Societies: An Empirical Studycited by 203
  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. 2024Towards Measuring and Modeling "Culture" in LLMs: A Surveycited by 166
  19. 2024Quantifying the Persona Effect in LLM Simulationscited by 164
  20. 2024Political Compass or Spinning Arrow? Towards More Meaningful Evaluations for Values and Opinions in Large Language Modelscited by 162
  21. 2022Probing Pre-Trained Language Models for Cross-Cultural Differences in Valuescited by 147
  22. 2023Co-Writing with Opinionated Language Models Affects Users' Viewscited by 145
  23. 2023Large Language Models Understand and Can be Enhanced by Emotional Stimulicited by 143
  24. 2021Can Machines Learn Morality? The Delphi Experimentcited by 140
  25. 2024Collective Constitutional AI: Aligning a Language Model with Public Inputcited by 120
  26. 2022Who is GPT-3? An Exploration of Personality, Values and Demographicscited by 112
  27. 2022The Ghost in the Machine has an American accent: value conflict in GPT-3cited by 105
  28. 2023Aligning Language Models to User Opinionscited by 98
  29. 2023Value Kaleidoscope: Engaging AI with Pluralistic Human Values, Rights, and Dutiescited by 97
  30. 2023CoMPosT: Characterizing and Evaluating Caricature in LLM Simulationscited by 94
  31. 2022When to Make Exceptions: Exploring Language Models as Accounts of Human Moral Judgmentcited by 93
  32. 2024Measuring Political Bias in Large Language Models: What Is Said and How It Is Saidcited by 89
  33. 2023Neurons in Large Language Models: Dead, N-gram, Positionalcited by 88
  34. 2024Aligning to Thousands of Preferences via System Message Generalizationcited by 84
  35. 2024The Political Preferences of LLMscited by 83
  36. 2024Defending Against Unforeseen Failure Modes with Latent Adversarial Trainingcited by 82
  37. 2023Sensitivity, Performance, Robustness: Deconstructing the Effect of Sociodemographic Promptingcited by 80
  38. 2022Moral Mimicry: Large Language Models Produce Moral Rationalizations Tailored to Political Identitycited by 71

50 most cited of 78 All 78 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 10; 2026: 6.

19 papers.

Sort:

By area:

  1. 2025LLM Generated Persona is a Promise with a Catchcited by 77
  2. 2025SimBench: Benchmarking the Ability of Large Language Models to Simulate Human Behaviorscited by 48
  3. 2025Normative Evaluation of Large Language Models with Everyday Moral Dilemmascited by 23
  4. 2024Algorithmic Fidelity of Large Language Models in Generating Synthetic German Public Opinions: A Case Studycited by 14
  5. 2024Do LLMs have Consistent Values?cited by 13
  6. 2024Measuring Human and AI Values Based on Generative Psychometrics with Large Language Modelscited by 13
  7. 2025MAKIEval: A Multilingual Automatic WiKidata-based Framework for Cultural Awareness Evaluation for LLMscited by 13
  8. 2025Navigating the Alignment-Calibration Trade-off: A Pareto-Superior Frontier via Model Mergingcited by 10
  9. 2025Survey Response Generation: Generating Closed-Ended Survey Responses In-Silico with Large Language Modelscited by 8
  10. 2026Many AI Analysts, One Dataset: Navigating the Agentic Data Science Multiversecited by 7
  11. 2025Better Aligned with Survey Respondents or Training Data? Unveiling Political Leanings of LLMs on U.S. Supreme Court Casescited by 2
  12. 2025Improving the Distributional Alignment of LLMs using Supervisioncited by 2
7 more
  1. 2025Reward Model Perspectives: Whose Opinions Do Reward Models Reward?cited by 1
  2. 2025Too Open for Opinion? Embracing Open-Endedness in Large Language Models for Social Simulationcited by 1
  3. 2026Steer Model beyond Assistant: Controlling System Prompt Strength via Contrastive Decodingcited by 1
  4. 2026Moral Lenses, Political Coordinates: Towards Ideological Positioning of Morally Conditioned LLMscited by 0
  5. 2026Can One-sided Arguments Lead to Response Change in Large Language Models?cited by 0
  6. 2026BavGround: A Benchmark for Regional Cultural Grounding and Dialect Competence in Bavariancited by 0
  7. 2026Cultural Misalignment in Large Language Models: Detection, Measurement, and Mitigation Through Targeted Fine-Tuningcited by 0