Take caution in using LLMs as human surrogates: Scylla ex machina
Abstract
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.
Study specs
The study evaluates the reasoning depth of various advanced LLMs through their performance on the 11-20 money request game, analyzing failure points related to input language, roles, and safeguarding.
- Authors
- Y Gao,D Lee,G Burtch,S Fazelpour
- Institution
- Boston University,Northeastern University
- Discipline
- Economics,Artificial Intelligence,Social Science
- Study Type
- Experimental Study
- Year
- 2024
- Human Data Platform
- Prolific
- Source
- View Source Google Scholar
Measured Outcomes
The ability of LLMs to replicate human-like behavior and reasoning distribution in the context of social science simulations.
Peer Review & Critical Discussion
Potential Selection Bias in 2023 Cohort
The participant pool shows a concerning overrepresentation of users from high-income demographics. Looking at Table 3, we can see that 78% of respondents had annual incomes above $75k, which significantly limits the generalizability of these findings to broader populations.
Non-naive Participants Issue
I've noticed a methodological concern regarding participant naivety. Given that Prolific users often complete multiple studies, there's a real risk that participants had prior exposure to similar experimental paradigms, which could confound the results.
RLHF Applicability to This Study Design
The implications for RLHF training pipelines are understated. If we accept the authors' conclusions about preference stability, this has direct consequences for how we should structure reward model training. The temporal decay effect described in Section 4.2 is particularly relevant.
Verify your expertise to join discussion
Create an account and verify your credentials to participate in peer discussions.