mlsanityData to 14 Oct 2026

Large Language Models, Machine-Assisted Cultural Analytics, and the Agentic Turn

arXiv 2610.12792 ↗First posted 8 Oct 2026cs.CY cs.CLcited by 0

On the map: LLM agents and tool use → Social simulation and multi-agent debate

Abstract (arXiv)

Technologies like large language models make it easier to convert cultural material into analyzable variables, while LLM-driven agentic systems extend machine assistance to other parts of the research workflow. Rather than a full how-to guide or an exhaustive review of recent LLM use cases, this chapter looks at some crucial aspects of this new paradigm as well as the bigger picture. I argue that these technologies expand the scale, methodological range, and scope for delegation, while the basic logic by which those measurements support cultural claims remains mostly unchanged.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use. Builds on 35 of its 81 references that are in the map. First posted on arXiv 8 Oct 2026.

Builds on

35 of 81 references.

References · 35

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  3. 2020Beyond Accuracy: Behavioral Testing of NLP models with CheckListcited by 1,006
  4. 2023ChatGPT Outperforms Crowd-Workers for Text-Annotation Taskscited by 870
  5. 2021Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpuscited by 492
  6. 2023Can Large Language Models Transform Computational Social Science?cited by 250
  7. 2023Can large language models provide useful feedback on research papers? A large-scale empirical analysiscited by 200
  8. 2026Towards End-to-End Automation of AI Researchcited by 159
  9. 2022Efficient Few-Shot Learning Without Promptscited by 137
  10. 2020SemEval-2020 Task 1: Unsupervised Lexical Semantic Change Detectioncited by 108
  11. 2025The Alternative Annotator Test for LLM-as-a-Judge: How to Statistically Justify Replacing Human Annotators with LLMscited by 74
  12. 2024OpenScholar: Synthesizing Scientific Literature with Retrieval-augmented LMscited by 72
23 more
  1. 2024Autonomous LLM-driven research from data to human-verifiable research paperscited by 53
  2. 2025Large Language Model Hacking: Quantifying the Hidden Risks of Using LLMs for Text Annotationcited by 50
  3. 2024Can Unconfident LLM Annotations Be Used for Confident Conclusions?cited by 49
  4. 2024Can LLMs Replace Manual Annotation of Software Engineering Artifacts?cited by 42
  5. 2024Divergent Creativity in Humans and Large Language Modelscited by 31
  6. 2023Experimental Narratives: A Comparison of Human Crowdsourced Storytelling and AI Storytellingcited by 27
  7. 2023(Why) Is My Prompt Getting Worse? Rethinking Regression Testing for Evolving LLM APIscited by 23
  8. 2023A Survey on Contextualised Semantic Shift Detectioncited by 22
  9. 2023Machine-assisted quantitizing designs: augmenting humanities and social sciences with artificial intelligencecited by 15
  10. 2025Provocations from the Humanities for Generative AI Researchcited by 10
  11. 2026How Far Are We From True Auto-Research?cited by 10
  12. 2023From Voices to Validity: Leveraging Large Language Models (LLMs) for Textual Analysis of Policy Stakeholder Interviewscited by 9
  13. 2026Computational Hermeneutics: Evaluating generative AI as a cultural technologycited by 8
  14. 2020Theory In, Theory Out: The uses of social theory in machine learning for social sciencecited by 4
  15. 2022Active sampling: A machine-learning-assisted framework for finite population inference with optimal subsamplescited by 4
  16. 2025Expertise elevates AI usage: experimental evidence comparing laypeople and professional artistscited by 4
  17. 2025Benchmarking Vision-Language and Multimodal Large Language Models in Zero-shot and Few-shot Scenarios: A study on Christian Iconographycited by 3
  18. 2022An Analytics of Culture: Modeling Subjectivity, Scalability, Contextuality, and Temporalitycited by 2
  19. 2024A dancing bear, a colleague, or a sharpened toolbox? The cautious adoption of generative AI technologies in digital humanities researchcited by 2
  20. 2025LLM Agents for Interactive Exploration of Historical Cadastre Data: Framework and Application to Venicecited by 1
  21. 2025Automating Iconclass: LLMs and RAG for Large-Scale Classification of Religious Woodcutscited by 1
  22. 2026Approaches to Analysing Historical Newspapers Using LLMscited by 1
  23. 2026Modeling Engagement with Brand and Organizational TikTok Videos Using Machine-Assisted Theory-Ensemble Annotationcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025'Too much alignment; not enough culture': Re-balancing cultural alignment practices in LLMs
  2. 2023CDEval: A Benchmark for Measuring the Cultural Dimensions of Large Language Models
  3. 2025Beyond Static Responses: Multi-Agent LLM Systems as a New Paradigm for Social Science Research
  4. 2024Survey of Cultural Awareness in Language Models: Text and Beyond
  5. 2026From Tokens To Agents: A Researcher's Guide To Understanding Large Language Models
  6. 2026Language Models as Measurement Apparatus for Culture
  7. 2024CulturalTeaming: AI-Assisted Interactive Red-Teaming for Challenging LLMs' (Lack of) Multicultural Knowledge
  8. 2025Randomness, Not Representation: The Unreliability of Evaluating Cultural Alignment in LLMs