Populism Meets AI: Advancing Populism Research with LLMs
Not on the map. Why?
Abstract (arXiv)
Measuring the ideational content of populism remains a challenge. Traditional strategies based on textual analysis have been critical for building the field's foundations and providing a valid, objective indicator of populist framing. Yet these approaches are costly, time consuming, and difficult to scale across languages, contexts, and large corpora. Here we present the results from a rubric and anchor guided chain of thought (CoT) prompting approach that mirrors human coder training. By leveraging the Global Populism Database (GPD), a comprehensive dataset of global leaders' speeches annotated for degrees of populism, we replicate the process used to train human coders by prompting the LLM with an adapted version of the same documentation to guide the model's reasoning. We then test multiple proprietary and open weight models by replicating scores in the GPD. Our findings reveal that this domain specific prompting strategy enables the LLM to achieve classification accuracy on par with expert human coders, demonstrating its ability to navigate the nuanced, context sensitive aspects of populism.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 18 of its 58 references that are in the map. First posted on arXiv 8 Oct 2025.
Builds on
18 of 58 references.
References · 18
- 2017Attention Is All You Needcited by 60,361
- 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
- 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
- 2023Qwen Technical Reportcited by 3,344
- 2021Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsitycited by 3,073
- 2025gpt-oss-120b & gpt-oss-20b Model Cardcited by 1,386
- 2023ChatGPT Outperforms Crowd-Workers for Text-Annotation Taskscited by 870
- 2022Out of One, Many: Using Language Models to Simulate Human Samplescited by 752
- 2021Scaling Vision with Sparse Mixture of Expertscited by 747
- 2023A Comprehensive Overview of Large Language Modelscited by 648
- 2023Can Large Language Models Transform Computational Social Science?cited by 250
- 2024How do Large Language Models Handle Multilingualism?cited by 150
6 more
- 2024Large Language Models Offer an Alternative to the Traditional Approach of Topic Modellingcited by 35
- 2024A Chain-of-Thought Prompting Approach with LLMs for Evaluating Students' Formative Assessment Responses in Sciencecited by 31
- 2024The Open Source Advantage in Large Language Models (LLMs)cited by 18
- 2025TRACT: Regression-Aware Fine-tuning Meets Chain-of-Thought Reasoning for LLM-as-a-Judgecited by 17
- 2025Prompting Science Report 2: The Decreasing Value of Chain of Thought in Promptingcited by 13
- 2024Larger Language Models Don't Care How You Think: Why Chain-of-Thought Prompting Fails in Subjective Taskscited by 8
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025Artificial Authority: From Machine Minds to Political Alignments. An Experimental Analysis of Democratic and Autocratic Biases in Large-Language Models
- 2024Political Bias in LLMs: Unaligned Moral Values in Agent-centric Simulations
- 2024GermanPartiesQA: Benchmarking Commercial Large Language Models and AI Companions for Political Alignment and Sycophancy
- 2026Sympathetic Framing: Evaluating AI Alignment across Sociodemographic Groups
- 2025Examining Alignment of Large Language Models through Representative Heuristics: The Case of Political Stereotypes
- 2026Mapping the Emerging Social Science of Large Language Models
- 2026LLM-Ideoplasticity: Measuring Ideological Plasticity in the Political Behavior of LLMs as a Context-Conditioned Distribution
- 2023Concept-Guided Chain-of-Thought Prompting for Pairwise Comparison Scoring of Texts with Large Language Models