Back to search

Article

Size Matters(?): Utilizing Small LLMs for Annotation in Social Science

2025-11-26

Abstract excerpt

Annotation is often a time-intensive and costly aspect of social sciences research utilizing natural language data. Recent advances in large language models (LLM) and general pretrained transformers promise new methods for quick and easy annotation but often rely on commercial APIs or cloud services that introduce costs, limit researcher control, and raise concerns about privacy. Bias from training data introduces...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work
5f82be1d-2cfc-5020-b699-8cec001ed1e4
DOI
10.20944/preprints202511.2016.v1
Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest
Interactive article relationship graphSelect a related publication card to move it into the centre and load its closest explainable connections. Solid lines are source-backed structured connections. Dashed lines are semantic discovery signals and are not scientific evidence.
Size Matters(?): Utilizing Small LLMs for Annotation in Social ScienceDOI 10.20944/preprints202511.2016.v1
Select a neighboring publication to make it the new centre.