Introducing HALC: A general pipeline for finding optimal prompting strategies for automated coding with LLMs in the computational social sciences

Abstract

LLMs are seeing widespread use for task automation, including automated coding in the social sciences. However, even though researchers have proposed different prompting strategies, their effectiveness varies across LLMs and tasks. Often trial and error practices are still widespread. We propose HALC$-$a general pipeline that allows for the systematic and reliable construction of optimal prompts for any given coding task and model, permitting the integration of any prompting strategy deemed relevant. To investigate LLM coding and validate our pipeline, we sent a total of 1,512 individual prompts to our local LLMs in over two million requests. We test prompting strategies and LLM task performance based on few expert codings (ground truth). When compared to these expert codings, we find prompts that code reliably for single variables ($α$climate = .76; $α$movement = .78) and across two variables ($α$climate = .71; $α$movement = .74) using the LLM Mistral NeMo. Our prompting strategies are set up in a way that aligns the LLM to our codebook$-$we are not optimizing our codebook for LLM friendliness. Our paper provides insights into the effectiveness of different prompting strategies, crucial influencing factors, and the identification of reliable prompts for each coding task and model.