Mapping how LLMs debate societal issues when shadowing human personality traits, sociodemographics and social media behavior
Not on the map. Why?
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.
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
13 of 57 references.
References · 13
- 2023Benchmarking Large Language Models for News Summarizationcited by 445
- 2023Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignmentcited by 401
- 2022Using cognitive psychology to understand GPT-3cited by 398
- 2023From Words to Watts: Benchmarking the Energy Costs of Large Language Model Inferencecited by 170
- 2024Is Temperature the Creativity Parameter of Large Language Models?cited by 93
- 2023When "A Helpful Assistant" Is Not Really Helpful: Personas in System Prompts Do Not Improve Performances of Large Language Modelscited by 53
- 2024Y Social: an LLM-powered Social Media Digital Twincited by 44
- 2020Text-mining forma mentis networks reconstruct public perception of the STEM gender gap in social mediacited by 8
- 2026OpenClaw AI Agents as Informal Learners at Moltbook: Characterizing an Emergent Learning Community at Scalecited by 8
- 2025Measuring and identifying factors of individuals' trust in Large Language Modelscited by 7
- 2026The Generative AI Paradox: GenAI and the Erosion of Trust, the Corrosion of Information Verification, and the Demise of Truthcited by 5
- 2023igraph enables fast and robust network analysis across programming languagescited by 4
Built on by
Citing papers per year: 2026: 2.
2 papers.
Similar, not cited
Close in wording, no citation either way
- 2023Do LLMs exhibit human-like response biases? A case study in survey design
- 2024White Men Lead, Black Women Help? Benchmarking and Mitigating Language Agency Social Biases in LLMs
- 2024With a Grain of SALT: Are LLMs Fair Across Social Dimensions?
- 2024Bias patterns in the application of LLMs for clinical decision support: A comprehensive study
- 2025In Silico Development of Psychometric Scales: Feasibility of Representative Population Data Simulation with LLMs
- 2025Better Aligned with Survey Respondents or Training Data? Unveiling Political Leanings of LLMs on U.S. Supreme Court Cases
- 2026Persona Prompting as a Lens on LLM Social Reasoning
- 2025Do LLMs Align Human Values Regarding Social Biases? Judging and Explaining Social Biases with LLMs