# Large language models struggle with ethnographic text annotation

arXiv: https://arxiv.org/abs/2601.12099 · HTML: https://mlsanity.com/paper/2601.12099/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 72 references that are in the map.
- First posted on arXiv 17 Jan 2026.

## Builds on (most cited first, 18 of 18)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems](https://mlsanity.com/paper/1905.00537/) (2019)
- [ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks](https://mlsanity.com/paper/2303.15056/) (2023)
- [Whose Opinions Do Language Models Reflect?](https://mlsanity.com/paper/2303.17548/) (2023)
- [Is ChatGPT a General-Purpose Natural Language Processing Task Solver?](https://mlsanity.com/paper/2302.06476/) (2023)
- [A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications](https://mlsanity.com/paper/2402.07927/) (2024)
- [Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond](https://mlsanity.com/paper/2304.13712/) (2023)
- [Social Simulacra: Creating Populated Prototypes for Social Computing Systems](https://mlsanity.com/paper/2208.04024/) (2022)
- [Can Large Language Models Transform Computational Social Science?](https://mlsanity.com/paper/2305.03514/) (2023)
- [Want To Reduce Labeling Cost? GPT-3 Can Help](https://mlsanity.com/paper/2108.13487/) (2021)
- [ChatGPT-4 Outperforms Experts and Crowd Workers in Annotating Political Twitter Messages with Zero-Shot Learning](https://mlsanity.com/paper/2304.06588/) (2023)
- [Concept Induction: Analyzing Unstructured Text with High-Level Concepts Using LLooM](https://mlsanity.com/paper/2404.12259/) (2024)
- [Opening up ChatGPT: Tracking openness, transparency, and accountability in instruction-tuned text generators](https://mlsanity.com/paper/2307.05532/) (2023)
- [LLMs as Research Tools: A Large Scale Survey of Researchers' Usage and Perceptions](https://mlsanity.com/paper/2411.05025/) (2024)
- [Open-Source LLMs for Text Annotation: A Practical Guide for Model Setting and Fine-Tuning](https://mlsanity.com/paper/2307.02179/) (2023)
- [Scalable Qualitative Coding with LLMs: Chain-of-Thought Reasoning Matches Human Performance in Some Hermeneutic Tasks](https://mlsanity.com/paper/2401.15170/) (2024)
- [H is for Human and How (Not) To Evaluate Qualitative Research in HCI](https://mlsanity.com/paper/2409.01302/) (2024)

## Built on by (most cited first, 2 of 2)

- [Observational Equivalence of LLM and Human Annotation](https://mlsanity.com/paper/2609.22133/) (2026)
- [Knowing Is Not Telling: Identity Ossification in LLM Representations of Trans-border Communities](https://mlsanity.com/paper/2610.12610/) (2026)

## Abstract (arXiv)

Large language models (LLMs) have shown promise for automated text annotation, raising hopes that they might accelerate cross-cultural research by extracting structured data from ethnographic texts. We evaluated 7 state-of-the-art LLMs on their ability to annotate 121 ritual features across 567 ethnographic excerpts. Performance was limited, falling well below levels required for reliable automated annotation. Longer texts, features requiring ordinal distinctions, and ambiguous constructs proved particularly difficult. Human inter-coder reliability set an approximate ceiling on LLM accuracy: features that human coders found difficult to agree upon were also difficult for LLMs. Yet even on features where humans reliably agreed, models fell short of human performance. Our findings suggest that LLMs cannot yet substitute for human expertise in ethnographic annotation.