The 1st Workshop on
LLMs and Generative AI for Finance
The 1st Workshop on LLMs and Generative AI
in Finance
Workshop at ICAIF '24
Workshop at ICAIF '24
Location: NYU Engineering Building, New York, USA
Time: November 14th, 2024, 13:00 - 17:30 EST
Paper submission deadline: October 16th, 2024 (AoE)
Acceptance notification: October 30th, 2024
Contact: contact@ai4f.org
This workshop is hosted as part of ICAIF (https://ai-finance.org/).
To attend, participant will need to register for ICAIF.
Call for papers
Location
NYU Engineering Building,
New York, USA
Paper submission deadline
October 16th, 2024 (AoE)
Call for papers
Acceptance notification
October 30th, 2024
Contact
contact@ai4f.org
This workshop is hosted as part of ICAIF (https://ai-finance.org/). To attend, participants will need to register for ICAIF.
Time
November 14th, 2024,
13:00 - 17:30 EST
Speakers
Speakers
Keynote
Valeri Nikolaev
University of Chicago,
Booth School of Business
Keynote
Andrew Lo
MIT, Sloan School of Management
Keynote
Ralph Koijen
University of Chicago,
Booth School of Business
Opening Remarks
Yoon Kim
MIT, Electrical Engineering and
Computer Science
Short talk
Sean Cao
University of Maryland,
Robert H. Smith School of Business
Short talk
Miao Liu
Boston College, Carroll School of Management
Short talk
Armineh Nourbakhsh
J.P. Morgan AI Research
Executive Director
Panelists
Organizing Committee
Organizing Committee
Prof. Yoon Kim
MIT, Electrical Engineering
and Computer Science
Prof. Valeri Nikolaev
University of Chicago, Booth School of Business
Prof. Andrew Lo
MIT, Sloan School of Management
Dr. Jacob
Chanyeol Choi
Linq
Prof. Alejandro
Lopez Lira
University of Florida, Warrington College of Business
Prof. Eric So
MIT, Sloan School of Management
Dr. Yu Yu
BlackRock
Prof. Jy-yong Sohn
Yonsei University,
Department of Applied Statistics
Prof. Elizabeth
Blankespoor
University of Washington,
Foster School of Business
Prof. Yoon Kim
MIT Electrical Engineering
and Computer Science
(EECS)
Prof. Valeri Nikolaev
University of Chicago Booth School of Business
Prof. Andrew Lo
MIT Sloan School of Management
Prof. Alejandro
Lopez Lira
Warrington College of Business, University of Florida
Dr. Jacob
Chanyeol Choi
Linq
Prof. Eric So
MIT Sloan School of Management
Prof. Elizabeth
Blankespoor
Foster School of Business,
University of Washington
Alex Kim
PhD Candidate, University of Chicago Booth School of Business
Dr. Yu Yu
BlackRock
Prof. Jy-yong Sohn
School of Business,
Yonsei University
David Kim
PhD Candidate, MIT Sloan School of Management
Sangwon Yoon, Esq
Seoul National University
Dr. Georgios
Papaioannou
Qube Research & Technologies
The goal of the workshop is
to study how large language models (LLMs) and generative AI can be used for finance and accounting applications.
The goal of the workshop is
to bridge the gap between advancements in Large Language Models (LLMs) and Natural Language Processing (NLP) and their application in finance and accounting.
It aims to address the challenges of using these technologies in the financial domain, such as handling unstructured data, context window limitations, hallucinations, and the need for interpretability.
About
the workshop
About
the workshop
The rapid advancements in large language models (LLMs) and generative AI more broadly have significantly impacted the interpretation and utilization of unstructured financial data, enabling a wide range of applications in finance and accounting. While LLMs have unlocked new possibilities in this domain, NLP techniques more broadly remain vital for various applications such as financial analysis, case studies, price forecasting, portfolio optimization, and analyzing financial reports and alternative data. They are also crucial in financial risk modeling, such as credit assessment, bankruptcy detection, and M&A target prediction using news sentiment and topic detection.
However, LLMs and NLP techniques face challenges in the financial domain, including the limited context window of LLMs, the complexities of converting unstructured data into structured formats, hallucinations, and the need for interpretability in financial applications. This workshop aims to bridge the gap between technological advancements in computer science and the specific needs of finance and accounting. By focusing on methodologies such as fine-tuning, retrieval-augmented generation (RAG), prompt engineering, and NLP, we aim to showcase how these techniques can improve the accuracy and relevance of insights derived from financial and accounting data. The ultimate goal is to foster interdisciplinary collaboration, enhance industry solutions, and contribute to academic research in finance and accounting.
The workshop will be held in conjunction with the ICAIF ’24 and is exclusively an in-person event.
The rapid advancements in large language models (LLMs) and generative AI more broadly have significantly impacted the interpretation and utilization of unstructured financial data, enabling a wide range of applications in finance and accounting. While LLMs have unlocked new possibilities in this domain, NLP techniques more broadly remain vital for various applications such as financial analysis, case studies, price forecasting, portfolio optimization, and analyzing financial reports and alternative data. They are also crucial in financial risk modeling, such as credit assessment, bankruptcy detection, and M&A target prediction using news sentiment and topic detection.
However, LLMs and NLP techniques face challenges in the financial domain, including the limited context window of LLMs, the complexities of converting unstructured data into structured formats, hallucinations, and the need for interpretability in financial applications. This workshop aims to bridge the gap between technological advancements in computer science and the specific needs of finance and accounting. By focusing on methodologies such as fine-tuning, retrieval-augmented generation (RAG), prompt engineering, and NLP, we aim to showcase how these techniques can improve the accuracy and relevance of insights derived from financial and accounting data. The ultimate goal is to foster interdisciplinary collaboration, enhance industry solutions, and contribute to academic research in finance and accounting.
The workshop will be held in conjunction with the ICAIF ’24 and is exclusively an in-person event.
We invite papers addressing domain-specific problems in finance and accounting, utilizing AI. While we encourage applications that involve the use of LLMs, we also invite papers that use generative AI technologies (broadly construed) to address problems in finance and accounting. Potential topics include but are not limited to:
We invite papers addressing domain-specific tasks in finance and accounting, utilizing techniques in LLMs and NLP. While the use of LLMs is recommended, submissions are not limited to LLMs and may include broader NLP methodologies. Potential topics include but are not limited to:
Methodologies for Processing Unstructured Data
Techniques to construct structured data from unstructured financial data using LLMs and NLP.
Technical Challenges of LLMs and NLP
Addressing issues such as hallucination, interpretability, and the integration of NLP methods in financial applications.
Prompt Engineering
Optimizing LLM prompts to extract relevant financial insights.
Retrieval-Augmented Generation (RAG)
Integrating external data sources with LLMs and NLP techniques for enhanced information retrieval.
Fine-Tuning LLMs
Customizing LLMs for specific financial applications to improve accuracy and relevance.
Text-to-SQL Applications
Translating natural language queries into SQL for querying structured databases using LLMs and NLP.
Evaluation Techniques
Enhancing the verifiability of generated text by LLMs and NLP methods to streamline manual verification processes.
Applications in Analyzing Financial Reports and Alternative Data
Utilizing LLMs and NLP for analyzing financial documents, news, SEC filings, and alternative data such as social media and video content.
Financial Risk Modeling
Applying LLMs and NLP in credit assessment, bankruptcy detection, and other risk modeling scenarios.
Multi-Lingual ESG Identification and Assessment
everaging LLMs and NLP for automated ESG scoring and identifying ESG issues across languages.
Financial Fraud Detection
Using NLP approaches, including those involving LLMs, for detecting fraud in financial transactions.
Enhancing Investor Communication
Utilizing LLMs and NLP to improve investor relations and communication.
Retrieval-Augmented Generation (RAG)
Integrating external data sources with LLMs and NLP techniques for enhanced information retrieval.
Fine-Tuning LLMs
Customizing LLMs for specific financial applications to improve accuracy and relevance.
Text-to-SQL Applications
Translating natural language queries into SQL for querying structured databases using LLMs and NLP.
Retrieval-Augmented Generation (RAG)
Integrating external data sources with LLMs and NLP techniques for enhanced information retrieval.
Fine-Tuning LLMs
Customizing LLMs for specific financial applications to improve accuracy and relevance.
Text-to-SQL Applications
Translating natural language queries into SQL for querying structured databases using LLMs and NLP.
Retrieval-Augmented Generation (RAG)
Integrating external data sources with LLMs and NLP techniques for enhanced information retrieval.
Fine-Tuning LLMs
Customizing LLMs for specific financial applications to improve accuracy and relevance.
Text-to-SQL Applications
Translating natural language queries into SQL for querying structured databases using LLMs and NLP.
Retrieval-Augmented Generation (RAG)
Integrating external data sources with LLMs and NLP techniques for enhanced information retrieval.
Fine-Tuning LLMs
Customizing LLMs for specific financial applications to improve accuracy and relevance.
Text-to-SQL Applications
Translating natural language queries into SQL for querying structured databases using LLMs and NLP.
Evaluation Techniques
Enhancing the verifiability of generated text by LLMs and NLP methods to streamline manual verification processes.
Applications in Analyzing Financial Reports and Alternative Data
Utilizing LLMs and NLP for analyzing financial documents, news, SEC filings, and alternative data such as social media and video content.
Financial Risk Modeling
Applying LLMs and NLP in credit assessment, bankruptcy detection, and other risk modeling scenarios.
Evaluation Techniques
Enhancing the verifiability of generated text by LLMs and NLP methods to streamline manual verification processes.
Applications in Analyzing Financial Reports and Alternative Data
Utilizing LLMs and NLP for analyzing financial documents, news, SEC filings, and alternative data such as social media and video content.
Financial Risk Modeling
Applying LLMs and NLP in credit assessment, bankruptcy detection, and other risk modeling scenarios.
Evaluation Techniques
Enhancing the verifiability of generated text by LLMs and NLP methods to streamline manual verification processes.
Applications in Analyzing Financial Reports and Alternative Data
Utilizing LLMs and NLP for analyzing financial documents, news, SEC filings, and alternative data such as social media and video content.
Financial Risk Modeling
Applying LLMs and NLP in credit assessment, bankruptcy detection, and other risk modeling scenarios.
Evaluation Techniques
Enhancing the verifiability of generated text by LLMs and NLP methods to streamline manual verification processes.
Applications in Analyzing Financial Reports and Alternative Data
Utilizing LLMs and NLP for analyzing financial documents, news, SEC filings, and alternative data such as social media and video content.
Financial Risk Modeling
Applying LLMs and NLP in credit assessment, bankruptcy detection, and other risk modeling scenarios.
Multi-Lingual ESG Identification and Assessment
everaging LLMs and NLP for automated ESG scoring and identifying ESG issues across languages.
Financial Fraud Detection
Using NLP approaches, including those involving LLMs, for detecting fraud in financial transactions.
Enhancing Investor Communication
Utilizing LLMs and NLP to improve investor relations and communication.
Multi-Lingual ESG Identification and Assessment
everaging LLMs and NLP for automated ESG scoring and identifying ESG issues across languages.
Financial Fraud Detection
Using NLP approaches, including those involving LLMs, for detecting fraud in financial transactions.
Enhancing Investor Communication
Utilizing LLMs and NLP to improve investor relations and communication.
Multi-Lingual ESG Identification and Assessment
everaging LLMs and NLP for automated ESG scoring and identifying ESG issues across languages.
Financial Fraud Detection
Using NLP approaches, including those involving LLMs, for detecting fraud in financial transactions.
Enhancing Investor Communication
Utilizing LLMs and NLP to improve investor relations and communication.
Multi-Lingual ESG Identification and Assessment
everaging LLMs and NLP for automated ESG scoring and identifying ESG issues across languages.
Financial Fraud Detection
Using NLP approaches, including those involving LLMs, for detecting fraud in financial transactions.
Enhancing Investor Communication
Utilizing LLMs and NLP to improve investor relations and communication.
Methodologies for Processing Unstructured Data
Techniques to construct structured data from unstructured financial data using LLMs and NLP.
Technical Challenges of LLMs and NLP
Addressing issues such as hallucination, interpretability, and the integration of NLP methods in financial applications.
Prompt Engineering
Optimizing LLM prompts to extract relevant financial insights.
Retrieval-Augmented Generation (RAG)
Integrating external data sources with LLMs and NLP techniques for enhanced information retrieval.
Fine-Tuning LLMs
Customizing LLMs for specific financial applications to improve accuracy and relevance.
Text-to-SQL Applications
Translating natural language queries into SQL for querying structured databases using LLMs and NLP.
Evaluation Techniques
Enhancing the verifiability of generated text by LLMs and NLP methods to streamline manual verification processes.
Applications in Analyzing Financial Reports and Alternative Data
Utilizing LLMs and NLP for analyzing financial documents, news, SEC filings, and alternative data such as social media and video content.
Financial Modeling
Applying LLMs and AI for credit assessment, price forecasting, bankruptcy detection, and other financial modeling scenarios.
Multi-Lingual ESG Identification and Assessment
everaging LLMs and NLP for automated ESG scoring and identifying ESG issues across languages.
Financial Fraud Detection
Using NLP approaches, including those involving LLMs, for detecting fraud in financial transactions.
Enhancing Investor Communication
Utilizing LLMs and NLP to improve investor relations and communication.
Submission
Guidelines
Submission Guidelines
There is no length limit or strict format requirement. While formatting according to ACM guidelines is recommended (see below), we encourage submissions in an open format to allow the authors to focus on content with formatting restrictions. Submissions should be in PDF format and can be directly submitted as they are.
The workshop is non-archival and will not have official proceedings.
Recommended Formatting:
Recommended Formatting:
Additional Requirements
Additional Requirements
For each submission, at least one author must agree to serve as a reviewer and deliver their reviews on time.
The author list cannot be modified after the initial submission, except before printing.
Any changes after acceptance will be communicated directly with the authors.
Key Dates
Key Dates
Submission Deadline
October 16th, 2024 (Anywhere on Earth)
October 16th, 2024
(Anywhere on Earth)
Author Notification
October 30th, 2024
Workshop
November 14th, 2024 (Thursday, 13:00 - 17:30 Eastern Time)
Submission Process
Submissions are to be made through the OpenReview platform (link to be updated: https://openreview.net/). Authors must submit the paper content (PDF document), title, author names, contact details, and a brief abstract electronically through the workshop’s submission site. At least one author of each accepted paper is required to attend the conference to present their work.
Review Process
This workshop will follow a single-blind review process, where authors’ identities are known to the reviewers, but reviewers’ identities are not disclosed to the authors. There will be no rebuttal period, and all submissions will be treated with strict confidentiality.
Accepted Papers
All accepted papers will be invited to participate in the poster session. Details on poster format and printing requirements will be provided by the organizers after acceptance. The organizers will handle the printing of the posters, so participants do not need to print them themselves. Selected papers may also be given the opportunity for oral presentation, subject to scheduling constraints.
The workshop is non-archival and will not have official proceedings. Only the author names and titles of accepted papers will appear on the website, with no disclosure of any content.
Schedule
Schedule
Opening Remarks
1:00 PM - 1:05 PM (5 minutes)
Opening Remarks
1:00 PM - 1:05 PM (5 minutes)
Keynote 1
1:05 PM - 1:35 PM (30 minutes)
Keynote 1
1:05 PM - 1:35 PM (30 minutes)
Short Talk 1
1:35 PM - 1:50 PM (15 minutes)
1:35 PM - 1:50 PM (15 minutes)
Keynote 2
1:50 PM - 2:20 PM (30 minutes)
1:50 PM - 2:20 PM (30 minutes)
Coffee Break
2:20 PM - 2:40 PM (20 minutes)
2:20 PM - 2:40 PM (20 minutes)
Keynote 3
2:40 PM - 3:10 PM (30 minutes)
2:40 PM - 3:10 PM (30 minutes)
Short Talk 2
3:10 PM - 3:25 PM (15 minutes)
3:10 PM - 3:25 PM (15 minutes)
Panel Discussion
3:25 PM - 4:00 PM (35 minutes)
3:25 PM - 4:00 PM (35 minutes)
Short Talk 3
4:00 PM - 4:15 PM (15 minutes)
4:00 PM - 4:15 PM (15 minutes)
Short Talk 4
4:15 PM - 4:30 PM (15 minutes)
4:15 PM - 4:30 PM (15 minutes)
Poster Session & Coffee
4:30 PM - 5:30 PM (60 minutes)
4:30 PM - 5:30 PM (60 minutes)
Contact
Contact
For further details and submission guidelines, please contact the workshop organizers at
For further details and submission guidelines,
please contact the workshop organizers at