# Web-Browsing LLMs Can Access Social Media Profiles and Infer User Demographics

arXiv: https://arxiv.org/abs/2507.12372 · HTML: https://mlsanity.com/paper/2507.12372/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 47 references that are in the map.
- First posted on arXiv 16 Jul 2025.

## Builds on (most cited first, 27 of 27)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer](https://mlsanity.com/paper/1904.06690/) (2019)
- [ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks](https://mlsanity.com/paper/2303.15056/) (2023)
- [Benchmarking Large Language Models for News Summarization](https://mlsanity.com/paper/2301.13848/) (2023)
- [Can Large Language Models Transform Computational Social Science?](https://mlsanity.com/paper/2305.03514/) (2023)
- [Multilingual Machine Translation with Large Language Models: Empirical Results and Analysis](https://mlsanity.com/paper/2304.04675/) (2023)
- [Human heuristics for AI-generated language are flawed](https://mlsanity.com/paper/2206.07271/) (2022)
- [PALR: Personalization Aware LLMs for Recommendation](https://mlsanity.com/paper/2305.07622/) (2023)
- [How would Stance Detection Techniques Evolve after the Launch of ChatGPT?](https://mlsanity.com/paper/2212.14548/) (2022)
- [Towards Open-World Recommendation with Knowledge Augmentation from Large Language Models](https://mlsanity.com/paper/2306.10933/) (2023)
- [Online Human-Bot Interactions: Detection, Estimation, and Characterization](https://mlsanity.com/paper/1703.03107/) (2017)
- [Detecting Hate Speech with GPT-3](https://mlsanity.com/paper/2103.12407/) (2021)
- [ONCE: Boosting Content-based Recommendation with Both Open- and Closed-source Large Language Models](https://mlsanity.com/paper/2305.06566/) (2023)
- [Zero-Shot Next-Item Recommendation using Large Pretrained Language Models](https://mlsanity.com/paper/2304.03153/) (2023)
- [Designing a Dashboard for Transparency and Control of Conversational AI](https://mlsanity.com/paper/2406.07882/) (2024)
- [Adversarial Search Engine Optimization for Large Language Models](https://mlsanity.com/paper/2406.18382/) (2024)
- [SentimentGPT: Exploiting GPT for Advanced Sentiment Analysis and its Departure from Current Machine Learning](https://mlsanity.com/paper/2307.10234/) (2023)
- [Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution](https://mlsanity.com/paper/2506.01055/) (2025)
- [Demographic Inference and Representative Population Estimates from Multilingual Social Media Data](https://mlsanity.com/paper/1905.05961/) (2019)
- [Heterogeneous Knowledge Fusion: A Novel Approach for Personalized Recommendation via LLM](https://mlsanity.com/paper/2308.03333/) (2023)
- [User Modeling in the Era of Large Language Models: Current Research and Future Directions](https://mlsanity.com/paper/2312.11518/) (2023)
- [Enhancing Job Recommendation through LLM-based Generative Adversarial Networks](https://mlsanity.com/paper/2307.10747/) (2023)
- [Generative Job Recommendations with Large Language Model](https://mlsanity.com/paper/2307.02157/) (2023)
- [Fine-Tuning Llama 2 Large Language Models for Detecting Online Sexual Predatory Chats and Abusive Texts](https://mlsanity.com/paper/2308.14683/) (2023)
- [Clickbait Detection via Large Language Models](https://mlsanity.com/paper/2306.09597/) (2023)
- [The Only Way is Ethics: A Guide to Ethical Research with Large Language Models](https://mlsanity.com/paper/2412.16022/) (2024)
- [Data marketplaces can increase the willingness to share social media data at low prices](https://mlsanity.com/paper/2506.16618/) (2025)

## Built on by (most cited first, 3 of 3)

- [CrowdLLM: Building LLM-Based Digital Populations Augmented with Generative Models](https://mlsanity.com/paper/2512.07890/) (2025)
- [From Weak Cues to Real Identities: Evaluating Inference-Driven De-Anonymization in LLM Agents](https://mlsanity.com/paper/2603.18382/) (2026)
- [Unsupervised Elicitation of Moral Values from Language Models](https://mlsanity.com/paper/2601.17728/) (2026)

## Abstract (arXiv)

Large language models (LLMs) have traditionally relied on static training data, limiting their knowledge to fixed snapshots. Recent advancements, however, have equipped LLMs with web browsing capabilities, enabling real time information retrieval and multi step reasoning over live web content. While prior studies have demonstrated LLMs ability to access and analyze websites, their capacity to directly retrieve and analyze social media data remains unexplored. Here, we evaluate whether web browsing LLMs can infer demographic attributes of social media users given only their usernames. Using a synthetic dataset of 48 X (Twitter) accounts and a survey dataset of 1,384 international participants, we show that these models can access social media content and predict user demographics with reasonable accuracy. Analysis of the synthetic dataset further reveals how LLMs parse and interpret social media profiles, which may introduce gender and political biases against accounts with minimal activity. While this capability holds promise for computational social science in the post API era, it also raises risks of misuse particularly in information operations and targeted advertising underscoring the need for safeguards. We recommend that LLM providers restrict this capability in public facing applications, while preserving controlled access for verified research purposes.