Unintended Effects of Geographic Conditioning in Large Language Models

Naz Col, David M. Chan

Keywords: geographic bias, evaluation framework, leakage, Large Language Models

TL;DR: We show geographic location injected into LLM context consistently causes models to leak regional references into location-agnostic outputs.

Abstract: Modern conversational AI systems frequently rely on user metadata to localize responses, yet the unintended regional biases introduced by this hidden context remain poorly understood. In this work, we evaluate _location leakage_: the phenomenon where a model generates geographic references despite receiving a geographically neutral user prompt. Across both creative writing and open-ended Q\&A prompts, even state-of-the-art LLMs systematically favor region-specific outputs when exposed to location metadata, with leakage spiking by up to 793 times above baseline (e.g., from 0.04\% to 31.7\% for Llama 3.1-8B, and 21.3\% and 8.8\% for Qwen3-8B and Claude Sonnet 4.6, respectively). Our analysis further shows a novel structural conditioning effect: replacing the injected location with the placeholder "Unknown" still elevates leakage by up to 72 times above baseline, demonstrating that the user profile frame itself, independent of any geographic content, acts as a generative conditioning signal.

Email Sharing: We authorize the sharing of all author emails with Program Chairs.

Data Release: We authorize the release of our submission and author names to the public in the event of acceptance.

Submission Number: 46