mlsanityData to 7 Oct 2026

Take Caution in Using LLMs as Human Surrogates: Scylla Ex Machina

arXiv 2410.19599 ↗First posted 25 Oct 2024econ.GN cs.AI cs.CYcited by 29

On the map: LLM reasoning → Reasoning benchmarks and evaluation

Abstract (arXiv)

Recent studies suggest large language models (LLMs) can exhibit human-like reasoning, aligning with human behavior in economic experiments, surveys, and political discourse. This has led many to propose that LLMs can be used as surrogates or simulations for humans in social science research. However, LLMs differ fundamentally from humans, relying on probabilistic patterns, absent the embodied experiences or survival objectives that shape human cognition. We assess the reasoning depth of LLMs using the 11-20 money request game. Nearly all advanced approaches fail to replicate human behavior distributions across many models. Causes of failure are diverse and unpredictable, relating to input language, roles, and safeguarding. These results advise caution when using LLMs to study human behavior or as surrogates or simulations.

Key facts. Cited by 29 papers in the map (data through 7 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 36 of its 73 references that are in the map. First posted on arXiv 25 Oct 2024.

Builds on

36 of 73 references.

Closest ancestors · 6

Same direction, newest first

  1. 2024Easy Problems That LLMs Get Wrong30 May
  2. 2023Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks5 Jul
  3. 2023Large Language Models Are Not Strong Abstract Reasoners31 May
  4. 2023Testing the General Deductive Reasoning Capacity of Large Language Models Using OOD Examples24 May
  5. 2023LLMs as Factual Reasoners: Insights from Existing Benchmarks and Beyond23 May
  6. 2022Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?25 Feb

Other references · 30

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2023GPT-4 Technical Reportcited by 18,132
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  4. 2020Scaling Laws for Neural Language Modelscited by 6,411
  5. 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,193
  6. 2020Extracting Training Data from Large Language Modelscited by 2,144
  7. 2023Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Promptingcited by 1,081
  8. 2018The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networkscited by 847
  9. 2023Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formattingcited by 778
  10. 2023Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedbackcited by 743
  11. 2022Out of One, Many: Using Language Models to Simulate Human Samplescited by 737
  12. 2024A Survey on Large Language Models for Code Generationcited by 646
18 more
  1. 2022Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studiescited by 506
  2. 2023The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"cited by 399
  3. 2022Using cognitive psychology to understand GPT-3cited by 389
  4. 2023Understanding the Effects of RLHF on LLM Generalisation and Diversitycited by 386
  5. 2023Large Language Models Fail on Trivial Alterations to Theory-of-Mind Taskscited by 288
  6. 2023Don't Make Your LLM an Evaluation Benchmark Cheatercited by 194
  7. 2024Let's Think Dot by Dot: Hidden Computation in Transformer Language Modelscited by 186
  8. 2023The political ideology of conversational AI: Converging evidence on ChatGPT's pro-environmental, left-libertarian orientationcited by 183
  9. 2023Large Language Models Understand and Can be Enhanced by Emotional Stimulicited by 143
  10. 2023Can Large Language Models Infer Causation from Correlation?cited by 142
  11. 2023Language Models Meet World Models: Embodied Experiences Enhance Language Modelscited by 123
  12. 2024Beyond prompt brittleness: Evaluating the reliability and consistency of political worldviews in LLMscited by 55
  13. 2024Changing Answer Order Can Decrease MMLU Accuracycited by 41
  14. 2024Unveiling the Spectrum of Data Contamination in Language Models: A Survey from Detection to Remediationcited by 30
  15. 2024Do Large Language Models Perform the Way People Expect? Measuring the Human Generalization Functioncited by 24
  16. 2024Elephants Never Forget: Testing Language Models for Memorization of Tabular Datacited by 19
  17. 2024Evaluating AI Evaluation: Perils and Prospectscited by 11
  18. 2024Can Large Language Models Always Solve Easy Problems if They Can Solve Harder Ones?cited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 20; 2026: 8.

29 papers.

Sort:

By area:

  1. 2025LLM Social Simulations Are a Promising Research Methodcited by 97
  2. 2025Finetuning LLMs for Human Behavior Prediction in Social Science Experimentscited by 35
  3. 2025Beyond Demographics: Fine-tuning Large Language Models to Predict Individuals' Subjective Text Perceptionscited by 31
  4. 2025The simulation of judgment in LLMscited by 22
  5. 2025It's the Thought that Counts: Evaluating the Attempts of Frontier LLMs to Persuade on Harmful Topicscited by 13
  6. 2025A validity-guided workflow for robust large language model research in psychologycited by 8
  7. 2025PredictaBoard: Benchmarking LLM Score Predictabilitycited by 7
  8. 2025Moloch's Bargain: Emergent Misalignment When LLMs Compete for Audiencescited by 7
  9. 2025A Multi-Task Evaluation of LLMs' Processing of Academic Text Inputcited by 5
  10. 2025PersonaFuse: A Personality Activation-Driven Framework for Enhancing Human-LLM Interactionscited by 5
  11. 2024Static network structure cannot stabilize cooperation among Large Language Model agentscited by 4
  12. 2026The Illusion of Intervention: Your LLM-Simulated Experiment is an Observational Studycited by 4
17 more
  1. 2025Reasoning and the Trusting Behavior of DeepSeek and GPT: An Experiment Revealing Hidden Fault Lines in Large Language Modelscited by 2
  2. 2025Improving the Distributional Alignment of LLMs using Supervisioncited by 2
  3. 2025LISTEN to Your Preferences: An LLM Framework for Multi-Objective Selectioncited by 2
  4. 2025Reliable agent engineering should integrate machine-compatible organizational principlescited by 2
  5. 2025The LLM Wears Prada: Analysing Gender Bias and Stereotypes through Online Shopping Datacited by 1
  6. 2025Robustness is Important: Limitations of LLMs for Data Fittingcited by 1
  7. 2026The Collapse of Heterogeneity in Silicon Philosopherscited by 1
  8. 2026Statistical Foundations of LLM-based A/B Testing: A Surrogacy Framework for Human Causal Inferencecited by 1
  9. 2025Natural Language Generationcited by 0
  10. 2025Synthetic Data Generation for Screen Time and App Usagecited by 0
  11. 2025Estimating the Error of Large Language Models at Pairwise Text Comparisoncited by 0
  12. 2025Knowing Your Uncertainty -- On the application of LLM in social sciencescited by 0
  13. 2026Improving Behavioral Alignment in LLM Social Simulations via Context Formation and Navigationcited by 0
  14. 2026To Words and Beyond: Probing Large Language Models for Sentence-Level Psycholinguistic Norms of Memorability and Reading Timescited by 0
  15. 2026Will Scaling Improve Social Simulation with LLMs?cited by 0
  16. 2026Proxy-Validated LLM UX Micro-Simulations: An Artifact-First Protocol for Early-Stage Decision Supportcited by 0
  17. 2026Aplaud: Adaptive Personalized Low-Rank Decomposition for User-Specific LLMcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Evaluating LLMs as Human Surrogates in Controlled Experiments
  2. 2023The Challenge of Using LLMs to Simulate Human Behavior: A Causal Inference Perspective
  3. 2024Systematic Biases in LLM Simulations of Debates
  4. 2025Computational Basis of LLM's Decision Making in Social Simulation
  5. 2024LLM-driven Imitation of Subrational Behavior : Illusion or Reality?
  6. 2023Are LLMs the Master of All Trades? : Exploring Domain-Agnostic Reasoning Skills of LLMs
  7. 2025Humanizing LLMs: A Survey of Psychological Measurements with Tools, Datasets, and Human-Agent Applications
  8. 2025Noise, Adaptation, and Strategy: Assessing LLM Fidelity in Decision-Making