Skip to Main Content

Machines and Society

A growing guide on the latest in data-driven research and emerging technologies at the intersection of society, information and technology.

Introduction

In this section, we explore various approaches of utilizing generative AI as research assistants or research methods for data-driven research. Generative AI has the potential to enhance academic performance in multiple stages of scientific research, and can be done with caution in conjunction with human evaluation and interpretation. 
 
The major incentive for integrating generative AI into the research process is that it enables researchers to concentrate on the fundamental tasks by delegating supplementary responsibilities to generative AI. 

However, when conducting research with generative AI, it is crucial to evaluate the model's limitations and potential variability in performance. In the end, it is domain expertise, the ability to generate unique insights, and ethical considerations that will be essential in distinguishing research outcomes.

Coding Assistant for Data Analysis

One of the most apparent use cases is using generative AI as a coding assistant across various stages in the data workflow. Researchers can use the tool to

  • explain code in a step-by-step manner
  • ask "how to code" questions
  • translate between programming languages
  • generate sample code
  • complete code
  • optimize code for efficiency, simplicity, readability, and maintainability 
  • debug code

Note that generative AI's performance in these cases depends on the level of support for the particular language or software package. Additionally, researchers should be cautious about using generative AI for anything beyond coding assistance. Even tasks as seemingly straightforward like data cleaning require making many small decisions based on clearly defined objectives. Relying on generative AI for more complex tasks like model selection without evaluating the outputs is also not recommended.

Text Analysis

* This section is outdated and will be updated.

Researchers may leverage generative AI as a natural language processing tool for various tasks, including labeling topics, extracting entities, and assessing sentiments for given text data, among other tasks. 

There are some experiments using ChatGPT for tasks with potential for feature generation, including 

Note that this technique may be helpful for researchers to obtain preliminary understanding of their data and documents at the initial stages of research. However, the generation process is not transparent and arguably not reproducible when the full technical details of the model are absent, making it challenging to make informed decisions along the way. 

Social Simulations

LLMs are implicit computational models of humans (often referred to as homo silicus) by nature of their training on vast human-generated data. This makes them potent for building autonomous agents that simulate individuals and societies in single-agent setups, multi-agent systems, or human-AI interactions.

LLM agents are utilized in social simulations widely. They are constructed to explore social dynamics, develop or test theories of human behavior, or populate virtual spaces with realistic social phenomena. They provide ethical, scalable alternatives to real-world human studies, including topics very difficult to examine or populations very difficult to access. 

Economics

Horton, J. J. (2023). Large language models as simulated economic agents: What can we learn from homo silicus? (No. w31122). National Bureau of Economic Research.

 

Manning, B. S., Zhu, K., & Horton, J. J. (2024). Automated Social Science: Language Models as Scientist and Subjects (No. arXiv:2404.11794). arXiv. https://doi.org/10.48550/arXiv.2404.11794

 

Leng, Y. (2024). Folk Economics in the Machine: LLMs and the Emergence of Mental Accounting (SSRN Scholarly Paper No. 4705130). Social Science Research Network. https://doi.org/10.2139/ssrn.4705130

 

Social computing

Park, J. S., O’Brien, J. C., Cai, C. J., Morris, M. R., Liang, P., & Bernstein, M. S. (2023). Generative Agents: Interactive Simulacra of Human Behavior (No. arXiv:2304.03442). arXiv. https://doi.org/10.48550/arXiv.2304.03442

 

Gao, C., Lan, X., Lu, Z., Mao, J., Piao, J., Wang, H., Jin, D., & Li, Y. (2025). S3: Social-network Simulation System with Large Language Model-Empowered Agents (No. arXiv:2307.14984). arXiv. https://doi.org/10.48550/arXiv.2307.14984

 

Social theories

Aher, G. V., Arriaga, R. I., & Kalai, A. T. (2023). Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies. Proceedings of the 40th International Conference on Machine Learning, 337–371. https://proceedings.mlr.press/v202/aher23a.html

 

Törnberg, P., Valeeva, D., Uitermark, J., & Bail, C. (2023). Simulating Social Media Using Large Language Models to Evaluate Alternative News Feed Algorithms (No. arXiv:2310.05984). arXiv. https://doi.org/10.48550/arXiv.2310.05984

LLM agents use modular components to enhance human-like behavior in dynamic settings: profiling module to identify roles, memory module to recall past behaviors, planning module to plan future actions, and action module to translate the agent’s decisions into specific outputs.

Evaluation strategies of LLM agents include subjective assessments by human judges who score or rank agent outputs or differentiate them from human outputs, as well as quantitative metrics and standardized benchmarks. 

Deploying LLM agents for social simulations requires careful consideration, as model limitations may affect the accuracy of outputs or lead to unintended consequences.

Bias: LLMs tend to give responses not representative of the diverse public (see Bias section for more details). 

Alignment: LLMs are usually fine-tuned to align with human values. Besides, as a byproduct of fine-tuning, some models tend to be overly agreeable. However, an ideal social simulation of real-world problems may require representing negative human behaviors, which is often restricted.

Low variance of response distributions: LLMs generate less diverse responses than humans would.

Temporal gaps: The temporal information in LLM training data (e.g., from the internet) is often lost, making it risky to simulate historical contexts or current populations accurately if there's a gap between the model's training data cutoff and the period being modeled.

Cross-linguistic influence: If a model has been trained on a mixture of languages, knowledge and attitudes from one socio-linguistic system may affect others in the model. For instance, lthe internal representations can be partially language-agnostic, partially biased toward English-centric reasoning, and partially differentiated by language.

Lack of sensory experience: LLMs lack embodied experiences, limiting their understanding of real-world context.

Alien cognition: LLMs may at times deviate from natural human behavior, generating misleading human simulations. For instance, surprises that emerge from analysis may be misconstrued as discoveries when they are mere errors in simulation.

Knowledge boundary:  LLMs' vast knowledge can be disadvantageous when simulating scenarios requiring agents to operate with limited or specific knowledge, as they might make decisions based on information real users wouldn't have.

 

Dillion, D., Tandon, N., Gu, Y., & Gray, K. (2023). Can AI language models replace human participants? Trends in Cognitive Sciences, 27(7), 597–600. https://doi.org/10.1016/j.tics.2023.04.008

 

Shanahan, M., McDonell, K., & Reynolds, L. (2023). Role play with large language models. Nature, 623(7987), 493–498. https://doi.org/10.1038/s41586-023-06647-8

 

Wang, L., Ma, C., Feng, X., Zhang, Z., Yang, H., Zhang, J., Chen, Z., Tang, J., Chen, X., Lin, Y., Zhao, W. X., Wei, Z., & Wen, J. (2024). A survey on large language model based autonomous agents. Frontiers of Computer Science, 18(6), 186345. https://doi.org/10.1007/s11704-024-40231-1

 

Guo, T., Chen, X., Wang, Y., Chang, R., Pei, S., Chawla, N. V., Wiest, O., & Zhang, X. (2024). Large Language Model based Multi-Agents: A Survey of Progress and Challenges. arXiv. https://doi.org/10.48550/arXiv.2402.01680 [GitHub repo: Awesome LLM-based Multi-Agents Papers]

 

Bail, C. A. (2024). Can Generative AI improve social science? Proceedings of the National Academy of Sciences, 121(21), e2314021121. https://doi.org/10.1073/pnas.2314021121

 

Kozlowski, A. C., & Evans, J. (2025). Simulating Subjects: The Promise and Peril of Artificial Intelligence Stand-Ins for Social Agents and Interactions. Sociological Methods & Research, 54(3), 1017–1073. https://doi.org/10.1177/00491241251337316

Synthetic Data Generation

Contact

Yun Dai
Data Services
yun.dai@nyu.edu