{"ID":2841904,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.17572","arxiv_id":"2511.17572","title":"Community-Aligned Behavior Under Uncertainty: Evidence of Epistemic Stance Transfer in LLMs","abstract":"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.","short_abstract":"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: t...","url_abs":"https://arxiv.org/abs/2511.17572","url_pdf":"https://arxiv.org/pdf/2511.17572v1","authors":"[\"Patrick Gerard\",\"Aiden Chang\",\"Svitlana Volkova\"]","published":"2025-11-14T20:04:52Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.SI\"]","methods":"[\"Large Language Model\",\"Language Model\",\"Generative Adversarial Network\"]","has_code":false}