2026-09-19T05:56:37Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/1563392024-08-22T03:40:25Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023
Lo, Andrew W.
Ross, Jillian A.
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
2024-08-21T18:57:56Z
2024-08-21T18:57:56Z
2024-05
2024-07-10T12:59:53.396Z
https://hdl.handle.net/1721.1/156339
Humans are not homo economicus (i.e., rational economic beings). We exhibit systematic behavioral biases such as loss aversion, anchoring, framing, etc., which lead us to make suboptimal economic decisions. Insofar as such biases may embedded in text data on which large language models (LLMs) are trained, to what extent are LLMs prone to the same behavioral biases? Understanding these biases in LLMs is crucial for deploying LLMs to support human decision-making. To enable the responsible deployment of LLMs, I propose economic alignment. Economic alignment is a specific form of AI alignment that provides a critical perspective to interrogate what human preferences we would like to incorporate into LLM decisions. To illustrate the power of economic alignment, I systematically study the economic decision-making behaviors of LLMs through utility theory, a paradigm at the core of modern economic theory. I apply experimental designs from human studies to LLMs and find that they are neither entirely human-like nor entirely economicus-like. Specifically, I find that LLMs generally exhibit stronger inequity aversion, stronger loss aversion, weaker risk aversion, and stronger time discounting compared to human subjects. I further find that most LLMs struggle to maintain consistent economic behavior across settings. Finally, I present a case study that examines how we can intervene through prompting to better align LLMs with economic goals.
S.M.
Massachusetts Institute of Technology
Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)
Copyright retained by author(s)
https://creativecommons.org/licenses/by-nc-nd/4.0/
Examining LLMs in Economic Settings
Thesis
application/pdf
Master
Master of Science in Electrical Engineering and Computer Science
Publication
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="6182f6db-4ed6-4417-bc60-2a71abf1849b">
<Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type>
<Title>Examining LLMs in Economic Settings</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2024-05</PublicationDate>
<Authors>
<Author>
<DisplayName>Ross, Jillian A.</DisplayName>
<Affiliation>
<OrgUnit>
</OrgUnit>
</Affiliation>
</Author>
</Authors>
<Editors>
</Editors>
<Publishers>
<Publisher>
<DisplayName>Massachusetts Institute of Technology</DisplayName>
<OrgUnit />
</Publisher>
</Publishers>
<License>https://creativecommons.org/licenses/by-nc-nd/4.0/</License>
<Abstract>Humans are not homo economicus (i.e., rational economic beings). We exhibit systematic behavioral biases such as loss aversion, anchoring, framing, etc., which lead us to make suboptimal economic decisions. Insofar as such biases may embedded in text data on which large language models (LLMs) are trained, to what extent are LLMs prone to the same behavioral biases? Understanding these biases in LLMs is crucial for deploying LLMs to support human decision-making. To enable the responsible deployment of LLMs, I propose economic alignment. Economic alignment is a specific form of AI alignment that provides a critical perspective to interrogate what human preferences we would like to incorporate into LLM decisions. To illustrate the power of economic alignment, I systematically study the economic decision-making behaviors of LLMs through utility theory, a paradigm at the core of modern economic theory. I apply experimental designs from human studies to LLMs and find that they are neither entirely human-like nor entirely economicus-like. Specifically, I find that LLMs generally exhibit stronger inequity aversion, stronger loss aversion, weaker risk aversion, and stronger time discounting compared to human subjects. I further find that most LLMs struggle to maintain consistent economic behavior across settings. Finally, I present a case study that examines how we can intervene through prompting to better align LLMs with economic goals.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>