Method note
Where LLMs help in CSS — and where they don't (Ziems et al.)
Benchmark of LLMs on many computational-social-science coding tasks, with practical guidance on when to use them.
What is reported
The authors find LLMs are reasonable zero-shot coders for some classification tasks but fall short of fine-tuned models on many, and recommend them as an aid to human annotation.
Before you use it
Results reflect the models tested at the time; re-check on your task and current models.
Sources and review
Source checked · Not tested by this site
Checked the public abstract and bibliographic record. Results describe the authors' study, not a replication by this site.
License and reuse
No license has been recorded. Check the source’s license before reusing code, models or data.
A license note is not a license audit. Open source does not guarantee free hosting, model access or commercial reuse.