Large Language Models

---

This week we will discuss the use of large language models (LLMs) in social science research and what are the implications of improvements in LLMs for such classical tasks as text annotation.

Required Readings

• Jurafsky and Martin 2026 Ch 7 Large Language Models
• Benoit, Kenneth, Scott De Marchi, Conor Laver, Michael Laver, and Jinshuai Ma. 2025. “Using Large Language Models to Analyze Political Texts through Natural Language Understanding.” American Journal of Political Science, Forthcoming. https://kenbenoit.net/pdfs/Benoit_etal_2025_AJPS.pdf

Additional Readings

• Bisbee, James, and Arthur Spirling. 2026. “What to Do When Humans Are No Longer the Gold Standard: Large Language Models, State of the Art and Robustness for Politics Research.” Working Paper. https://github.com/ArthurSpirling/futureProofR/blob/main/Bisbee_Spirling_human_gold_standard_2_10_2026.pdf