# Mapping how LLMs debate societal issues when shadowing human personality traits, sociodemographics and social media behavior

arXiv: https://arxiv.org/abs/2604.27624 · HTML: https://mlsanity.com/paper/2604.27624/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 57 references that are in the map.
- First posted on arXiv 30 Apr 2026.

## Builds on (most cited first, 13 of 13)

- [Benchmarking Large Language Models for News Summarization](https://mlsanity.com/paper/2301.13848/) (2023)
- [Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment](https://mlsanity.com/paper/2308.05374/) (2023)
- [Using cognitive psychology to understand GPT-3](https://mlsanity.com/paper/2206.14576/) (2022)
- [From Words to Watts: Benchmarking the Energy Costs of Large Language Model Inference](https://mlsanity.com/paper/2310.03003/) (2023)
- [Is Temperature the Creativity Parameter of Large Language Models?](https://mlsanity.com/paper/2405.00492/) (2024)
- [When "A Helpful Assistant" Is Not Really Helpful: Personas in System Prompts Do Not Improve Performances of Large Language Models](https://mlsanity.com/paper/2311.10054/) (2023)
- [Y Social: an LLM-powered Social Media Digital Twin](https://mlsanity.com/paper/2408.00818/) (2024)
- [Text-mining forma mentis networks reconstruct public perception of the STEM gender gap in social media](https://mlsanity.com/paper/2003.08835/) (2020)
- [OpenClaw AI Agents as Informal Learners at Moltbook: Characterizing an Emergent Learning Community at Scale](https://mlsanity.com/paper/2602.18832/) (2026)
- [Measuring and identifying factors of individuals' trust in Large Language Models](https://mlsanity.com/paper/2502.21028/) (2025)
- [The Generative AI Paradox: GenAI and the Erosion of Trust, the Corrosion of Information Verification, and the Demise of Truth](https://mlsanity.com/paper/2601.00306/) (2026)
- [igraph enables fast and robust network analysis across programming languages](https://mlsanity.com/paper/2311.10260/) (2023)
- [MOSAIC: Unveiling the Moral, Social and Individual Dimensions of Large Language Models](https://mlsanity.com/paper/2603.00048/) (2026)

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

- [MyMentorLLM: A psychotherapy GenAI environment with multimodal voice/text patients, trainees and experts for deliberate practice](https://mlsanity.com/paper/2607.25667/) (2026)
- [Natural Language Processing Psychometrics](https://mlsanity.com/paper/2608.07316/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) can strongly shape social discourse, yet datasets investigating how LLM outputs vary across controlled social and contextual prompting remain sparse. Cognitive Digital Shadows (CDS) is a 190,000-record synthetic corpus supporting analyses of LLM-generated discourse. Each CDS record is generated by one of 19 LLMs, prompted to shadow either a human persona or an AI-assistant role. CDS contains LLM responses on 4 controversial societal topics: vaccines/healthcare, social media disinformation, the gender gap in science, and STEM stereotypes. Persona-conditioned records encode 17 sociodemographic and psychological attributes, providing data linking LLMs' prompts, language, stances and reasoning. Texts are validated for topic anchoring and can support emotional analyses via interpretable NLP (e.g. textual forma mentis networks). CDS is enriched by a pooling platform with user-friendly dashboards, enabling easy, interactive group-level comparisons of emotional and semantic framing across personas, topics and models. The CDS prompting framework supports future audits of LLMs' bias, social sensitivity and alignment.