@inproceedings{chawla-etal-2025-evaluating,
title = "Evaluating {AI} for Finance: Is {AI} Credible at Assessing Investment Risk Appetite?",
author = "Chawla, Divij and
Bhutada, Ashita and
Do, Duc Anh and
Raghunathan, Abhinav and
Sp, Vinod and
Guo, Cathy and
Liew, Dar Win and
Gupta, Prannaya and
Bhardwaj, Rishabh and
Bhardwaj, Rajat and
Poria, Soujanya",
editor = "Potdar, Saloni and
Rojas-Barahona, Lina and
Montella, Sebastien",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = nov,
year = "2025",
address = "Suzhou (China)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-industry.189/",
pages = "2828--2839",
ISBN = "979-8-89176-333-3",
abstract = "We assess whether AI systems can credibly evaluate investment risk appetite{---}a task that must be thoroughly validated before automation. Our analysis was conducted on proprietary systems (GPT, Claude, Gemini) and open-weight models (LLaMA, DeepSeek, Mistral), using carefully curated user profiles that reflect real users with varying attributes such as country and gender. As a result, the models exhibit significant variance in score distributions when user attributes{---}such as country or gender{---}that should not influence risk computation are changed. For example, GPT-4o assigns higher risk scores to Nigerian and Indonesian profiles. While some models align closely with expected scores in the low- and mid-risk ranges, none maintain consistent scores across regions and demographics, thereby violating AI and finance regulations."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chawla-etal-2025-evaluating">
<titleInfo>
<title>Evaluating AI for Finance: Is AI Credible at Assessing Investment Risk Appetite?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Divij</namePart>
<namePart type="family">Chawla</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ashita</namePart>
<namePart type="family">Bhutada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Duc</namePart>
<namePart type="given">Anh</namePart>
<namePart type="family">Do</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abhinav</namePart>
<namePart type="family">Raghunathan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vinod</namePart>
<namePart type="family">Sp</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cathy</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dar</namePart>
<namePart type="given">Win</namePart>
<namePart type="family">Liew</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Prannaya</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rishabh</namePart>
<namePart type="family">Bhardwaj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rajat</namePart>
<namePart type="family">Bhardwaj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Soujanya</namePart>
<namePart type="family">Poria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Saloni</namePart>
<namePart type="family">Potdar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lina</namePart>
<namePart type="family">Rojas-Barahona</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastien</namePart>
<namePart type="family">Montella</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou (China)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-333-3</identifier>
</relatedItem>
<abstract>We assess whether AI systems can credibly evaluate investment risk appetite—a task that must be thoroughly validated before automation. Our analysis was conducted on proprietary systems (GPT, Claude, Gemini) and open-weight models (LLaMA, DeepSeek, Mistral), using carefully curated user profiles that reflect real users with varying attributes such as country and gender. As a result, the models exhibit significant variance in score distributions when user attributes—such as country or gender—that should not influence risk computation are changed. For example, GPT-4o assigns higher risk scores to Nigerian and Indonesian profiles. While some models align closely with expected scores in the low- and mid-risk ranges, none maintain consistent scores across regions and demographics, thereby violating AI and finance regulations.</abstract>
<identifier type="citekey">chawla-etal-2025-evaluating</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-industry.189/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>2828</start>
<end>2839</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluating AI for Finance: Is AI Credible at Assessing Investment Risk Appetite?
%A Chawla, Divij
%A Bhutada, Ashita
%A Do, Duc Anh
%A Raghunathan, Abhinav
%A Sp, Vinod
%A Guo, Cathy
%A Liew, Dar Win
%A Gupta, Prannaya
%A Bhardwaj, Rishabh
%A Bhardwaj, Rajat
%A Poria, Soujanya
%Y Potdar, Saloni
%Y Rojas-Barahona, Lina
%Y Montella, Sebastien
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou (China)
%@ 979-8-89176-333-3
%F chawla-etal-2025-evaluating
%X We assess whether AI systems can credibly evaluate investment risk appetite—a task that must be thoroughly validated before automation. Our analysis was conducted on proprietary systems (GPT, Claude, Gemini) and open-weight models (LLaMA, DeepSeek, Mistral), using carefully curated user profiles that reflect real users with varying attributes such as country and gender. As a result, the models exhibit significant variance in score distributions when user attributes—such as country or gender—that should not influence risk computation are changed. For example, GPT-4o assigns higher risk scores to Nigerian and Indonesian profiles. While some models align closely with expected scores in the low- and mid-risk ranges, none maintain consistent scores across regions and demographics, thereby violating AI and finance regulations.
%U https://aclanthology.org/2025.emnlp-industry.189/
%P 2828-2839
Markdown (Informal)
[Evaluating AI for Finance: Is AI Credible at Assessing Investment Risk Appetite?](https://aclanthology.org/2025.emnlp-industry.189/) (Chawla et al., EMNLP 2025)
ACL
- Divij Chawla, Ashita Bhutada, Duc Anh Do, Abhinav Raghunathan, Vinod Sp, Cathy Guo, Dar Win Liew, Prannaya Gupta, Rishabh Bhardwaj, Rajat Bhardwaj, and Soujanya Poria. 2025. Evaluating AI for Finance: Is AI Credible at Assessing Investment Risk Appetite?. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 2828–2839, Suzhou (China). Association for Computational Linguistics.