Researchers find intuitive prompts improve LLM social media simulation
A new study on arXiv tested how well language models simulate individual reactions to social media posts. Researchers profiled eight Serbian participants through questionnaires, interviews, and self-presentations. They then asked four language models to predict those reactions under five different prompt conditions, varying profile content and instruction style.
Key points
- Eight Serbian participants profiled via questionnaires, interviews, and self-presentations
- Four language models tested under five prompt conditions for social media reaction prediction
- Intuitive prompts improved fidelity, especially on unfamiliar topics, per arXiv study
The study found that attitudinal content improved prediction accuracy over demographic backstories. Agents aligned more closely with their assigned profiles than participants did with their own survey answers. Prompts instructing models to respond intuitively and immediately—rather than analytically—yielded the highest fidelity. This method reduced the compression of individual differences and performed best on unfamiliar topics, suggesting these agents could serve as general-purpose simulated users.
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Research
All →- Researchers release benchmark for AI in systematic review screening · 1 src
- SlideLab framework generates scientific presentations from research papers · 1 src
- Cartograph reduces AI agent tool discovery from O(n) to O(k) · 1 src
- Survey reviews 211 fake review detection studies from 2018 to 2026 · 1 src
- Researchers audit LLM-as-judge in text-to-SQL pipeline, find low agreement · 1 src
Comments
via GitHub Discussions