Building Bibliographic Superwork Clusters for Discovery with Local LLMs

Matt Miller

About

Building Bibliographic Superwork Clusters for Discovery with Local LLMs

Judging work relationships in 88K clusters

Aug 13 2026

Intro

Links and Clusters

Local LLM + Data

Relationship Vocabulary

Quality Evaluation

OPAC Browse Interface

Summary

Intro

In bibliographic description you are able to build relationships to external authorities and records in various ways. In MARC you can use controlled vocabularies which eventually evolved the ability to use identifiers and URIs to establish connections. You can link to other titles specifically via a Name Title authority or some description in the higher 7XX fields mostly used for Serial cataloging. As we move into more FRBR-LRM/WEMI/Linked Data aligned standards like Bibframe relationships become more central to how the record is constructed. The Work and the Instance are separate resources, the Bibframe Hub takes the place of and expands the functionality of Name Title Authorities for cataloging purposes. There are more details I’m glossing over here because I’m thinking about the type of relationships that can be built for discovery rather than cataloging. The following little experiment is looking at automated ways to build relationships that aggregate works under the idea of a Superwork: The novel, the translation, the movie adaptation, the 13 different editions, all linked with their relationships defined.

Links and Clusters

While Hubs do collocation they are similar to Named Title authorities in that they are scoped to specific levels of expression and like all authority work it takes additional effort while cataloging meaning there are very specific rules to when one is created. This idea of Superwork is much more expansive and is of course not a new idea, lots of debate about the role of Works vs something higher. The Share-VDE project implemented a Superwork level they called an Opus that is discussed in this paper. So it’s not a novel idea, it might be a good idea, but the problem is that it’s hard to implement for a number of reasons.

Clustering bibliographic data is also a well trodden path. Twenty-five years ago orgs like OCLC were clustering works for FRBR-ization efforts. The process involves matching parts of MARC records on various fields to create groupings of resources. So clustering is “easy” but once they are clustered how do you relate them to one another? You have to come up with elaborate rule based processes that quickly fall apart against records described at different levels of completeness, conflicting historical practices and an infinite long tail of problems.

Local LLM + Data

Enter the idea of using a LLM to help you judge how all these works are related to one another. I’m an AI pragmatic, I’ve been subjected to a couple demos and pitches this year of AI “cataloging” books and I find that sort of approach to AI in libraries really harmful and gross. I think LLMs can potentially be useful for specific tasks or workflow automations. And I think it has a place in this idea of enriching legacy data. I’ve also been really interested in using local models that can run on your own (beefy) computer as alternatives to expensive black box frontier models.

So this test is going to be:

Cluster a catalog’s worth of records into works

Use a local LLM to judge what is the Superwork of the cluster and how all the works relate to it

Test how well it did and how useful are the results.

For the source data I’m going to use the Library of Congress catalog. I do work there but this is a side project (🫠) and I’m using their public downloadable bulk data. To cluster this catalog I wanted to cast a ridiculously wide net, so it looks for things that have the same title and a matching 1XX or 7XX contributor. This will miss things like translated titles (Der Idiot vs The Idiot) or transliterated titles but I use Name Title authorities to try to fill in those gaps. Applying this insane clustering methodology we get the following breakdown out of the ~20M records:

Full candidate universe (1,969,233 title+name matches → union-find merged)

Cluster sizeClusters% of clustersResources% of resources

21,068,03875.9%2,136,07651.8%<br>3–4245,63217.5%802,33419.5%<br>5–9 69,157 4.9% 424,928 10.3%<br>10–19 15,853 1.1% 204,028 4.9%<br>20–40 4,846 0.3% 130,465 3.2%<br>41–1002,0070.14%123,2843.0%<br>101–5009050.06%157,0273.8%<br>501–1,000570.004%38,6360.9%<br>1,001+ (max 21,188 — generic-title noise)300.002%107,4752.6%<br>Total 1,406,525 100%4,124,253 100%

So only 20% of records possibly belong to a cluster. The biggest cluster is 2 things, these clusters are often artifacts of MARC cataloging where two formats of the same work are recorded separately (print + ebook for example). For my test I wanted to do a significantly challenging cluster size, but don&rsquo;t want to do everything. I picked the 5-40 slice as a...