About the Indexer
I am a lifelong reader and a former reference librarian and book cataloger. My many years at a public library reference desk taught me a lot about how people seek information and I've applied that knowledge to creating indexes that anticipate the needs of the reader. I am a generalist with a broad knowledge base.
I have formal training in indexing and hold a B.A. in English and a Masters in Library and Information Science. Through my membership in the American Society for Indexing (ASI) , I participate in continuing education webinars, regional and national conferences, and online discussion forums with other indexers. I have served on the Executive Board of ASI as both Secretary (2020-2023) and President (2024-2025) and am a member of the Digital Publications Special Interest Group.
MLIS, Library and Information Science, 1987
University of Wisconsin-Milwaukee
Beta Phi Mu Honor Society
Bachelor of Arts, English
Oklahoma State University, Stillwater. Humanities secondary concentration
About AI and Indexing
I do not use AI in indexing. I use thought and judgment to create an index that will help your readers find the information they need. Please see below the ASI Digital Publications Indexing Special Interest Group's statement on AI in indexing.
American Society for Indexing (ASI) Digital Publications Indexing Special Interest Group on the
Role of AI in Indexing
Our current assessment is that using large language model AIs (LLMs) such as ChatGPT to generate indexes does not produce results that come anywhere near meeting our standards for excellence in Indexing. We also advise that documents not be uploaded or shared with LLMs without explicit client permission.
These LLMs fail at the indexer’s primary task: to ensure readers find needed information. Tests have shown that LLMs typically under index book-length works, do not provide adequate structure or cross-references, and can insert false information (hallucinations) into the index.* Each of these is problematic:
Future developments in AI may bring improvements, but at present we conclude the human brain of a professional indexer is still the best tool for analyzing, writing, and editing an index in full awareness of context as per quality standards.
*Bartmess, Elizabeth, “AI: Where You Can Use It and Where You Shouldn’t,” May 31, 2025, ISC/SCI Conference 2025 “Location! Location! Location”.
For an in-depth review of the current state of AI and indexing, click on the link below for the recent 2025 study:
"Can the Current Generation of LLMS Produce an Adequate Index?
I am a lifelong reader and a former reference librarian and book cataloger. My many years at a public library reference desk taught me a lot about how people seek information and I've applied that knowledge to creating indexes that anticipate the needs of the reader. I am a generalist with a broad knowledge base.
I have formal training in indexing and hold a B.A. in English and a Masters in Library and Information Science. Through my membership in the American Society for Indexing (ASI) , I participate in continuing education webinars, regional and national conferences, and online discussion forums with other indexers. I have served on the Executive Board of ASI as both Secretary (2020-2023) and President (2024-2025) and am a member of the Digital Publications Special Interest Group.
MLIS, Library and Information Science, 1987
University of Wisconsin-Milwaukee
Beta Phi Mu Honor Society
Bachelor of Arts, English
Oklahoma State University, Stillwater. Humanities secondary concentration
About AI and Indexing
I do not use AI in indexing. I use thought and judgment to create an index that will help your readers find the information they need. Please see below the ASI Digital Publications Indexing Special Interest Group's statement on AI in indexing.
American Society for Indexing (ASI) Digital Publications Indexing Special Interest Group on the
Role of AI in Indexing
Our current assessment is that using large language model AIs (LLMs) such as ChatGPT to generate indexes does not produce results that come anywhere near meeting our standards for excellence in Indexing. We also advise that documents not be uploaded or shared with LLMs without explicit client permission.
These LLMs fail at the indexer’s primary task: to ensure readers find needed information. Tests have shown that LLMs typically under index book-length works, do not provide adequate structure or cross-references, and can insert false information (hallucinations) into the index.* Each of these is problematic:
- Severe under-indexing, with as few as 20-40% of the access points of human-generated indexes, can prevent readers from locating desired information and mislead them into thinking that omitted information isn’t in the book at all
- Absent/near-absent index structure, especially cross-references, prevents the reader from effectively navigating to subtopics and related topics while misrepresenting the focus of the book
- Hallucinations (including invented page references and even wholly nonexistent topics) waste the reader’s time and break the trust between the reader and the book
Future developments in AI may bring improvements, but at present we conclude the human brain of a professional indexer is still the best tool for analyzing, writing, and editing an index in full awareness of context as per quality standards.
*Bartmess, Elizabeth, “AI: Where You Can Use It and Where You Shouldn’t,” May 31, 2025, ISC/SCI Conference 2025 “Location! Location! Location”.
For an in-depth review of the current state of AI and indexing, click on the link below for the recent 2025 study:
"Can the Current Generation of LLMS Produce an Adequate Index?
Quattro Indexing Service | mobile: 317.385.3231 | [email protected]
