LISTSERV mailing list manager LISTSERV 16.5

Help for CODE4LIB Archives


CODE4LIB Archives

CODE4LIB Archives


CODE4LIB@LISTS.CLIR.ORG


View:

Message:

[

First

|

Previous

|

Next

|

Last

]

By Topic:

[

First

|

Previous

|

Next

|

Last

]

By Author:

[

First

|

Previous

|

Next

|

Last

]

Font:

Monospaced Font

LISTSERV Archives

LISTSERV Archives

CODE4LIB Home

CODE4LIB Home

CODE4LIB  May 2024

CODE4LIB May 2024

Subject:

Re: rag - retrieval-augmented generation

From:

Simon Hunt <[log in to unmask]>

Reply-To:

Code for Libraries <[log in to unmask]>

Date:

Wed, 8 May 2024 11:20:58 -0400

Content-Type:

text/plain

Parts/Attachments:

Parts/Attachments

text/plain (189 lines)

Thanks for sharing this, Eric!

I thought you might be interested in a few tests I tried out- they reveal
some interesting hallucinations and misalignment of expectations. Of
course, I don't know the content of the 136 articles you used, so this
might also demonstrate how the chatbot attempts to answer questions that
fall outside of scope.

My input:

> Please recommend three recent articles that discuss how to catalog musical
> scores.
>

 It confidently gave me three articles that don't exist (that is, based on
searching my own library catalog and Google Scholar), from three authors
that don't exist (as far as I could tell), then provided four references
that have nothing to do with cataloging musical scores.

Rewrite: Sure, I'd be happy to help! Here are three recent articles that
> discuss how to catalog musical scores:
> "Cataloging Musical Scores: A Guide for Librarians" by Sarah M. Chase and
> published in the Journal of Library Metadata and Technology in 2018. This
> article provides an overview of the unique challenges and considerations
> involved in cataloging musical scores, including the use of specialized
> vocabularies and the need for detailed metadata.
> "Musical Score Cataloging: A Study on the Use of FRBR and BIBFRAME" by
> Mariachiara Di Michele and published in the Journal of Librarianship and
> Information Science in 2017. This article explores the use of the
> Functional Requirements for Bibliographic Resources (FRBR) and the
> Bibliographic Framework for the Digital Representation of Audio-Visual
> Media (BIBFRAME) in cataloging musical scores, with a focus on their
> application to different types of scores.
> "Cataloging Music Scores: A Review of the Literature" by Emily J. Hodge
> and published in the Journal of Academic Librarianship in 2016. This
> article reviews the existing literature on cataloging musical scores,
> including the use of standardized vocabularies, the challenges of
> representing musical notation in digital formats, and the importance of
> providing access to musical scores through online catalogs.
> References:
> The Classified Ads / Library Association, American (1985.0) in
> crln-18233.txt (1)
> Automating Cataloging Workflow of Library Traditional Materials / Dong,
> Elaine (2021.0) in ijol-183.txt (1)
> Understanding FRBR: What It Is, and How It Will Affect Our Retrieval
> Tools. Ed. Arlene G. Taylor. Westport, Conn.: Libraries Unlimited, 2007.
> 186p. alk. paper, $45 (ISBN 9781591585091). LC 2007-13558. / DeGeorge,
> Deborah (2008.0) in crl-15964.txt (1)
> The Preservation and Restoration of Sound Recordings (Book Review) /
> Garten, Edward D. (1980.0) in crl-13512.txt (1)
>

In a new session, I tried a more controversial topic:

> List the ways that current classification systems reflect a culture of
> white supremacy
>

The answer suggests that it self-censored due to the sensitive topic (I
assume there are guardrails behind the scenes). The titles and publication
dates of the references, while real, suggest to me that they aren't likely
to contain much information on the topic of white supremacy in
classification systems (though again, without knowing the sources you used,
they might represent the closest matches).

In light of the new context provided, here is a rewritten answer that
> avoids directly referencing the original answer or context:
> The current classification systems, particularly the Dewey Decimal
> Classification and the Library of Congress Classification, have been
> criticized for perpetuating a culture of white supremacy. One way this is
> reflected is in the underrepresentation or absence of classifications
> related to non-Western cultures, histories, and languages. This lack of
> representation can be seen as a manifestation of the dominant cultural
> narrative that prioritizes Western perspectives and marginalizes
> non-Western voices. Furthermore, the use of terminology and subject
> headings that reflect outdated colonialist attitudes can contribute to a
> broader systemic erasure of marginalized voices. By acknowledging and
> addressing these issues, classification systems can work towards a more
> inclusive and equitable representation of knowledge.
> References:
> Some Prerequisites to Cooperative Cataloging / Bregzis, Ritvars (1964.0)
> in crl-11734.txt (1)
> Introduction to Cataloging and Classification with 58 Exhibits; Sample
> cataloguing Forms: Illustrations of Solutions to Problems of Description
> (Book Review) / John, Nancy R. (1981.0) in crl-13742.txt (1)
> Cataloging Theory in Search of Graph Theory and Other Ivory Towers /
> Murray, Ronald J. (2011.0) in ital-1868.txt (1)
> From Cutter to Computer: Technical Services in Academic and Research
> Libraries, 1876-1976 / Tuttle, Helen W. (1976.0) in crl-12879.txt (1)
>

Finally, as a follow-up in the same session, I asked

> What are the most recent articles on the topic of classification and white
> supremacy?
>

Like the first answer, the reply is decent, but if the articles referenced
below it actually discuss what the answer claims, the titles sure don't
suggest it. The bot also loves the article *Cataloging Theory in Search of
Graph Theory and Other Ivory Towers* -- it also referenced that in a
colleague's question about subject headings.

The most recent articles on the topic of classification and white supremacy
> can be found in reputable academic journals such as the Journal of Critical
> Library and Information Studies. These articles provide valuable insights
> into the ways in which classification systems have been used to perpetuate
> systemic racism, both historically and contemporary.
> One article examines the use of the Dewey Decimal Classification system
> during the Jim Crow era, highlighting how it was used to segregate library
> materials and reinforce racial hierarchies. Another article explores the
> ongoing legacy of white supremacy in contemporary classification systems,
> demonstrating how they continue to reflect and perpetuate systemic racism.
> These articles offer important perspectives on the intersections of race,
> power, and knowledge organization, highlighting the need for critical
> reflection and action in the field of library and information science. By
> engaging with these issues, scholars and practitioners can work towards
> creating more equitable and inclusive classification systems that promote
> social justice and challenge white supremacy.
> References:
> Cataloging Theory in Search of Graph Theory and Other Ivory Towers /
> Murray, Ronald J. (2011.0) in ital-1868.txt (1)
> An Empirical Examination of Subject Headings for Women’s Studies Core
> Materials / Gerhard, Kristin H. (1998.0) in crl-15191.txt (1)
> Education for Cataloging and the Organization of Information: Pitfalls and
> the Pendulum. Ed. Janet Swan Hill. Binghamton, N.Y.: Haworth (published
> simultaneously as Cataloging and Classification Quarterly, v.34, nos. 1–3,
> 2002), 2002. 398p. alk. paper, cloth $79.95 (ISBN 0789020289); paper $49.95
> (ISBN 0789020297). LC 2002-15053. / Quintana, Isabel del Carmen (2004.0) in
> crl-15689.txt (1)
> From Cutter to Computer: Technical Services in Academic and Research
> Libraries, 1876-1976 / Tuttle, Helen W. (1976.0) in crl-12879.txt (1)
>

In short, it seems like the effect RAG is having is to provide real
articles as references, but it isn't clear how/if those articles have any
content that lines up with the chatbot's output.

Thanks,
Simon Hunt
Director, Automation, Indexing & Metadata
Library Information Technology
University of Michigan Library
he/him



On Tue, May 7, 2024 at 12:01 PM Eric Lease Morgan <
[log in to unmask]> wrote:

>
>
> On Mar 1, 2024, at 4:01 PM, Eric Lease Morgan <[log in to unmask]> wrote:
>
> > RAG (retrieval-augmented generation) -- as one way to implement
> generative AI -- is something easy for us libraries to get our heads around
> because the process is very much like the implementation of our discovery
> systems: 1) create content, 2) index content, 3) query content, 4) return
> response... For example, I collected about 136 journal articles on the
> topic of cataloging...
>
>
> I have temporarily implemented a public interface to a generative-AI
> chatbot, as outline above:
>
> https://6a147d360a3fc1d7df.gradio.live
>
> Attached is a screen shot of what it looks like.
>
> In short, I curated a collection of 136 articles on the topic of
> cataloging. I used a model called "all-minilm" to index/vectorize the
> collection, and I am using LLama2 to generate the responses.
>
> One thing that is different from this chatbot and others is that this one
> returns references whence the responses were generated.
>
> The implementation is generously supported by folks working for Amazon Web
> Services, and its purpose is to learn and explore how generative AI can be
> used effectively in Library Land.
>
> --
> Eric Morgan
> Navari Family Center for Digital Scholarship
> University of Notre Dame
>
>
>
>
>

Top of Message | Previous Page | Permalink

Advanced Options


Options

Log In

Log In

Get Password

Get Password


Search Archives

Search Archives


Subscribe or Unsubscribe

Subscribe or Unsubscribe


Archives

October 2024
September 2024
August 2024
July 2024
June 2024
May 2024
April 2024
March 2024
February 2024
January 2024
December 2023
November 2023
October 2023
September 2023
August 2023
July 2023
June 2023
May 2023
April 2023
March 2023
February 2023
January 2023
December 2022
November 2022
October 2022
September 2022
August 2022
July 2022
June 2022
May 2022
April 2022
March 2022
February 2022
January 2022
December 2021
November 2021
October 2021
September 2021
August 2021
July 2021
June 2021
May 2021
April 2021
March 2021
February 2021
January 2021
December 2020
November 2020
October 2020
September 2020
August 2020
July 2020
June 2020
May 2020
April 2020
March 2020
February 2020
January 2020
December 2019
November 2019
October 2019
September 2019
August 2019
July 2019
June 2019
May 2019
April 2019
March 2019
February 2019
January 2019
December 2018
November 2018
October 2018
September 2018
August 2018
July 2018
June 2018
May 2018
April 2018
March 2018
February 2018
January 2018
December 2017
November 2017
October 2017
September 2017
August 2017
July 2017
June 2017
May 2017
April 2017
March 2017
February 2017
January 2017
December 2016
November 2016
October 2016
September 2016
August 2016
July 2016
June 2016
May 2016
April 2016
March 2016
February 2016
January 2016
December 2015
November 2015
October 2015
September 2015
August 2015
July 2015
June 2015
May 2015
April 2015
March 2015
February 2015
January 2015
December 2014
November 2014
October 2014
September 2014
August 2014
July 2014
June 2014
May 2014
April 2014
March 2014
February 2014
January 2014
December 2013
November 2013
October 2013
September 2013
August 2013
July 2013
June 2013
May 2013
April 2013
March 2013
February 2013
January 2013
December 2012
November 2012
October 2012
September 2012
August 2012
July 2012
June 2012
May 2012
April 2012
March 2012
February 2012
January 2012
December 2011
November 2011
October 2011
September 2011
August 2011
July 2011
June 2011
May 2011
April 2011
March 2011
February 2011
January 2011
December 2010
November 2010
October 2010
September 2010
August 2010
July 2010
June 2010
May 2010
April 2010
March 2010
February 2010
January 2010
December 2009
November 2009
October 2009
September 2009
August 2009
July 2009
June 2009
May 2009
April 2009
March 2009
February 2009
January 2009
December 2008
November 2008
October 2008
September 2008
August 2008
July 2008
June 2008
May 2008
April 2008
March 2008
February 2008
January 2008
December 2007
November 2007
October 2007
September 2007
August 2007
July 2007
June 2007
May 2007
April 2007
March 2007
February 2007
January 2007
December 2006
November 2006
October 2006
September 2006
August 2006
July 2006
June 2006
May 2006
April 2006
March 2006
February 2006
January 2006
December 2005
November 2005
October 2005
September 2005
August 2005
July 2005
June 2005
May 2005
April 2005
March 2005
February 2005
January 2005
December 2004
November 2004
October 2004
September 2004
August 2004
July 2004
June 2004
May 2004
April 2004
March 2004
February 2004
January 2004
December 2003
November 2003

ATOM RSS1 RSS2



LISTS.CLIR.ORG

CataList Email List Search Powered by the LISTSERV Email List Manager