Evaluating large language models for domain-specific scholarly metadata classification

Muhammad Haris, Maryam Badar · 2026

Read Evaluating large language models for domain-specific scholarly metadata classification by Muhammad Haris, Maryam Badar (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13624084.txt.

Description

Muhammad Haris and Maryam Badar test, in 2026 work, whether open chat models can sort research papers into the right groups. Their field is work on models and computer runs of real systems. Each paper had to be tagged by trade field, by use area, and by the kind of method it used.

The pair tried five model groups and three ways of asking, with titles alone or with short texts added. The best setup scored just over half on a fair test scale. Method tags were the easiest to get right, while use area tags were the hardest. Adding the short text helped in all cases. The pair still urge human checks before such sorting is trusted on its own.

Catalog record

CREATORMuhammad Haris, Maryam Badar
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE51 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC13624084

Browse the full library · About the Tower of Babel