Can ChatGPT Help with Genealogy Citations?

This article originally appeared on See

If you’re curious about how artificial intelligence (AI) might help you become more efficient, consider experimenting with citations. The large language models (LLMs) that have become popular in the last year might prove useful in this area. I’ve been using ChatGPT to experiment with AI in the last month as a student in the National Genealogical Society (NGS) course, Empowering Genealogists with Artificial Intelligence taught by Steve Little. Steve has a great blog here: In the NGS course, we had four sessions about the four main LLM transformations: summarize, extract, generate, and translate. Today I experimented with having ChatGPT help me generate citations.

Book Citation

When learning how to create citations, it’s a good idea to start with a basic book citation. The principles for citing books are carried over to citing other publications in genealogy research, like websites. For genealogy citations, we use the Evidence Explained (EE) style. This style is based on the Chicago Manual’s Humanities Style (as opposed to its author-date style). The format for a book citation is the same in both EE and Chicago.

I asked ChatGPT 4 to help me cite a book in Chicago format. It then provided me both the format for a bibliographic entry and the footnote/endnote. Here’s the full response:

To cite the book “Research Like a Pro: A Genealogist’s Guide” by Diana Elder and Nicole Dyer in Chicago format, you would generally use the following structure:
Bibliography Entry: Elder, Diana, and Nicole Dyer. Research Like a Pro: A Genealogist’s Guide. [Place of Publication]: [Publisher], [Year of Publication].
  1. Diana Elder and Nicole Dyer, Research Like a Pro: A Genealogist’s Guide ([Place of Publication]: [Publisher], [Year of Publication]), [Page number].
In these citations, replace [Place of Publication], [Publisher], [Year of Publication], and [Page number] with the appropriate information from the book. The page number is only necessary in the footnote or endnote and should correspond to the specific part of the book you are referencing.
It’s important to note that the title of the book is italicized in both the bibliography and the notes. Additionally, in the notes, only the first author’s last name is listed first, followed by the first name, while the second author’s name is in the standard format.

Next I asked it how to create a shortened version of the reference note for use as a subsequent note. Here’s the response:

For a shortened version of the reference note for “Research Like a Pro: A Genealogist’s Guide” by Diana Elder and Nicole Dyer, used in subsequent notes in Chicago format, you would generally include just the primary author’s last name, a shortened version of the title, and the page number being referenced. It would look like this:
Elder and Dyer, Research Like a Pro, [Page number].
For instance, if you are referencing page 45 in a subsequent note, it would be:
Elder and Dyer, Research Like a Pro, 45.
This shortened format is used after the first full citation of the work in your footnotes or endnotes to make subsequent references more concise.

Read the full conversation here:

ChatGPT did a great job with providing the accurate format for a Chicago book citation. The Chicago Manual of Style, 17th ed., gives the same format on p. 799, section 14.101.

Census Citation

I asked ChatGPT to create a census citation. I started with a citation that I had already made for myself for my ancestor, Eliza Ann Isenhour. I separated the citation I had previously made into multiple lines, removed the punctuation, added an extra word (webpage near accessed) and put the civil division into the same line as the county and state – just to see if it knew where to put that. Here’s my prompt:

You are an expert genealogist. Make a citation for Eliza Isenhour on the 1850 census following the Evidence Explained style manual used by genealogists. Here is the information about Eliza’s enumeration:
1850 U.S. census
Polk, Montgomery County, Arkansas
population schedule
p. 405a
dwelling 6
family 6
Eliza Ann Isenhour in Barnet Isenhour household
database with images
webpage accessed 17 November 2023
citing NARA microfilm publication M432, roll 28

The response:

To create a citation for Eliza Isenhour in the 1850 U.S. Census following the Evidence Explained style, you would structure it like this:
“1850 U.S. census, Montgomery County, Arkansas, Polk, population schedule, p. 405a, dwelling 6, family 6, Eliza Ann Isenhour in Barnet Isenhour household; database with images, Ancestry ( : accessed 17 November 2023); citing NARA microfilm publication M432, roll 28.”
This citation follows the general format recommended by the Evidence Explained style guide, which includes the year and type of record, geographic location, specific details of where the record is found (page, dwelling, family), the individual’s name and household context, the database and its URL, the date of access, and the specific archival reference (NARA microfilm publication and roll number).

I was pretty impressed! It got almost everything right. This citation is usable. It did not place Polk, the civil division, in the correct position according to Evidence Explained, 3rd ed., p. 237. The civil division should follow the words “population schedule.” I prompted ChatGPT to put Polk where it belongs, and it did. I then asked it to make a few other tweaks, like removing the a after 405a, which is the page number given in the source information from Ancestry, and asked it to add the word (stamped) after 405. Then I asked it to italicize the publication website, Ancestry.

Read the full conversation here:

Checking Suggested Citations

It’s important to check for accuracy while ChatGPT is still evolving. Because LLMs aren’t search engines, they sometimes produce incorrect information, according to what it thinks you want to hear. When I asked ChatGPT to make a citation for Eliza Ann Isenhour on the 1850 census, without providing the details from her actual household, it suggested that I follow this format:

“1850 United States Federal Census, [State], [County], [Township or City], enumeration district [ED], page [Page Number], dwelling [Dwelling Number], family [Family Number], Eliza Isenhour; digital image, [Name of Database or Collection] ([URL of the database] : accessed [Date of Access]); citing National Archives and Records Administration microfilm [Microfilm Number].”

This is an okay suggestion, and I love that it created a template that you can fill in. However, it incorrectly tells you to include the enumeration district (ED). EDs were not used until the 1880 census. Read the full conversation here:

Why do LLMs produce incorrect suggestions? The GPT in ChatGPT stands for Generative Pre-trained Transformer. The AI has been trained by reading a lot of content and is best suited for helping you with creative tasks or helping you summarize a block of text that you provide. The way it works is by predicting what usually comes next when talking about specific topics. So, if you provide ChatGPT with the way you like your citations to look, then give it some information to use, it can probably help with that. While we’re still learning the capabilities of ChatGPT and other LLMs, it’s important to check their work. This will help you know if you can use it for the tasks that will help make your work more efficient.

Shortening Citations

Another usage you might try for ChatGPT and citations is asking it to shorten a citation you’ve already made, when you want to use it for a subsequent note. I returned to my first conversation with ChatGPT about creating a citation for Eliza Isenhour where I provided the details. After the full reference note citation was tweaked the way I like it, I asked it to shorten the citation for a subsequent note. Here’s the response:

For a subsequent note, a short form citation for Eliza Isenhour in the 1850 census can be created as follows:
“1850 U.S. census, Montgomery Co., Ark., Polk, p. 405 (stamped), Eliza Ann Isenhour.”
In this short form citation, the details are condensed, providing just enough information to identify the specific record without repeating all the information from the full citation. It includes the year, the abbreviated state and county, the civil division, page number, and the name of the individual.

My response:

Please include population schedule, abbreviated, and the dwelling and family numbers, which can also be abbreviated.

ChatGPT’s response:

Certainly! Here’s the revised short form citation including the requested elements:
“1850 U.S. census, Montgomery Co., Ark., pop. sch., Polk, p. 405 (stamped), dwl. 6, fam. 6, Eliza Ann Isenhour.”
In this version, “population schedule” is abbreviated as “pop. sch.,” and “dwelling” and “family” are abbreviated as “dwl.” and “fam.,” respectively. This format maintains the necessary details while being concise for a subsequent note.

This can be a starting point for helping you figure out how you want to shorten citations for subsequent notes in a particular piece of genealogical writing that you’re creating.


It seems possible that LLMs could help us start drafting our citations. However, without me providing the details for the 1850 census that I already knew would be helpful, it had a much harder time. Maybe we can train our chatbots to give us citations in the format we prefer after providing them with additional examples and training.

The book citation was great, so using ChatGPT for help citing common source types, like books and articles online, is a great usage right now.

Your Turn

If you experiment with asking ChatGPT to create a citation for you, share below in the comments how it turned out. Was the citation formatted the way you’d expect according to the style manual?

Note: If you are sharing any private information as you practice making citations, turn off your chat history so it’s not seen by the engineers training the chatbot. See for more info.

More AI and Genealogy Resources

Bettinger, Blaine.”Unlocking Family Secrets with AI | Findmypast,” 22 March 2023. YouTube. This webinar is a great introduction to  LLMs and Artificial Intelligence for genealogy and covers the purpose of LLMs, what they can do, and what they can’t do.

——. “10 ChatGPT Prompts Every Genealogist Needs to Know | Findmypast,” 10 May 2023. YouTube gives some great ideas for how to use ChatGPT in genealogy.

Little, Steve. “Empowering Genealogists with Artificial Intelligence 6 September 2023.” YouTube. This is an overview of AI for genealogy and some of the capabilities of ChatGPT.

——. “Artificial Intelligence and Genealogy: Using ChatGPT to Write Stories from Family Trees, Create Trees from Stories.” 17 March 2023. AI Genealogy Insights. This blog post discusses using ChatGPT to help create reports with citations and mentions the style guides used by genealogists.

This article originally appeared on See