# Magic Words or Methodical Work? Challenging Conventional Wisdom in LLM-Based Political Text Annotation

arXiv: https://arxiv.org/abs/2603.26898 · HTML: https://mlsanity.com/paper/2603.26898/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 30 of its 59 references that are in the map.
- First posted on arXiv 27 Mar 2026.

## Builds on (most cited first, 30 of 30)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Gemma 3 Technical Report](https://mlsanity.com/paper/2503.19786/) (2025)
- [gpt-oss-120b & gpt-oss-20b Model Card](https://mlsanity.com/paper/2508.10925/) (2025)
- [Model Cards for Model Reporting](https://mlsanity.com/paper/1810.03993/) (2018)
- [Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting](https://mlsanity.com/paper/2310.11324/) (2023)
- [A Survey on In-context Learning](https://mlsanity.com/paper/2301.00234/) (2022)
- [It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners](https://mlsanity.com/paper/2009.07118/) (2020)
- [Larger language models do in-context learning differently](https://mlsanity.com/paper/2303.03846/) (2023)
- [To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning](https://mlsanity.com/paper/2409.12183/) (2024)
- [Can Large Language Models Transform Computational Social Science?](https://mlsanity.com/paper/2305.03514/) (2023)
- [Marked Personas: Using Natural Language Prompts to Measure Stereotypes in Language Models](https://mlsanity.com/paper/2305.18189/) (2023)
- [From Words to Watts: Benchmarking the Energy Costs of Large Language Model Inference](https://mlsanity.com/paper/2310.03003/) (2023)
- [Quantifying the Persona Effect in LLM Simulations](https://mlsanity.com/paper/2402.10811/) (2024)
- [Does Prompt Formatting Have Any Impact on LLM Performance?](https://mlsanity.com/paper/2411.10541/) (2024)
- [ChatGPT-4 Outperforms Experts and Crowd Workers in Annotating Political Twitter Messages with Zero-Shot Learning](https://mlsanity.com/paper/2304.06588/) (2023)
- [Large Language Model Hacking: Quantifying the Hidden Risks of Using LLMs for Text Annotation](https://mlsanity.com/paper/2509.08825/) (2025)
- [Best Practices for Text Annotation with Large Language Models](https://mlsanity.com/paper/2402.05129/) (2024)
- [Open-Source LLMs for Text Annotation: A Practical Guide for Model Setting and Fine-Tuning](https://mlsanity.com/paper/2307.02179/) (2023)
- [Can GPT-4 Support Analysis of Textual Data in Tasks Requiring Highly Specialized Domain Expertise?](https://mlsanity.com/paper/2306.13906/) (2023)
- [Why Prompt Design Matters and Works: A Complexity Analysis of Prompt Search Space in LLMs](https://mlsanity.com/paper/2503.10084/) (2025)
- [Codebook LLMs: Evaluating LLMs as Measurement Tools for Political Science Concepts](https://mlsanity.com/paper/2407.10747/) (2024)
- [Prompt Design Matters for Computational Social Science Tasks but in Unpredictable Ways](https://mlsanity.com/paper/2406.11980/) (2024)
- [Prompt Stability Scoring for Text Annotation with Large Language Models](https://mlsanity.com/paper/2407.02039/) (2024)
- [Political DEBATE: Efficient Zero-shot and Few-shot Classifiers for Political Text](https://mlsanity.com/paper/2409.02078/) (2024)
- [Instruction Tuning Vs. In-Context Learning: Revisiting Large Language Models in Few-Shot Computational Social Science](https://mlsanity.com/paper/2409.14673/) (2024)
- [Memory Is All You Need: Testing How Model Memory Affects LLM Performance in Annotation Tasks](https://mlsanity.com/paper/2503.04874/) (2025)

## Abstract (arXiv)

Political scientists are rapidly adopting large language models (LLMs) for text annotation, yet the sensitivity of annotation results to implementation choices remains poorly understood. Most evaluations test a single model or configuration; how model choice, model size, learning approach, and prompt style interact, and whether popular "best practices" survive controlled comparison, are largely unexplored. We present a controlled evaluation of these pipeline choices, testing six open-weight models across four political science annotation tasks under identical quantisation, hardware, and prompt-template conditions. Our central finding is methodological: interaction effects dominate main effects, so seemingly reasonable pipeline choices can become consequential researcher degrees of freedom. No single model, prompt style, or learning approach is uniformly superior, and the best-performing model varies across tasks. Two corollaries follow. First, model size is an unreliable guide both to cost and to performance: cross-family efficiency differences are so large that some larger models are less resource-intensive than much smaller alternatives, while within model families mid-range variants often match or exceed larger counterparts. Second, widely recommended prompt engineering techniques yield inconsistent and sometimes negative effects on annotation performance. We use these benchmark results to develop a validation-first framework - with a principled ordering of pipeline decisions, guidance on prompt freezing and held-out evaluation, reporting standards, and open-source tools - to help researchers navigate this decision space transparently.