Saved in:
Bibliographic Details
Main Authors: Gerard, Patrick, Chang, Aiden, Volkova, Svitlana
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.17572
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • When large language models (LLMs) are aligned to a specific online community, do they exhibit generalizable behavioral patterns that mirror that community's attitudes and responses to new uncertainty, or are they simply recalling patterns from training data? We introduce a framework to test epistemic stance transfer: targeted deletion of event knowledge, validated with multiple probes, followed by evaluation of whether models still reproduce the community's organic response patterns under ignorance. Using Russian--Ukrainian military discourse and U.S. partisan Twitter data, we find that even after aggressive fact removal, aligned LLMs maintain stable, community-specific behavioral patterns for handling uncertainty. These results provide evidence that alignment encodes structured, generalizable behaviors beyond surface mimicry. Our framework offers a systematic way to detect behavioral biases that persist under ignorance, advancing efforts toward safer and more transparent LLM deployments.