# Community-Aligned Behavior Under Uncertainty: Evidence of Epistemic Stance Transfer in LLMs

arXiv: https://arxiv.org/abs/2511.17572 · HTML: https://mlsanity.com/paper/2511.17572/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 35 references that are in the map.
- First posted on arXiv 14 Nov 2025.

## Builds on (most cited first, 19 of 19)

- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [How Can We Know What Language Models Know?](https://mlsanity.com/paper/1911.12543/) (2019)
- [Whose Opinions Do Language Models Reflect?](https://mlsanity.com/paper/2303.17548/) (2023)
- [Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security](https://mlsanity.com/paper/2401.05459/) (2024)
- [Can Large Language Models Transform Computational Social Science?](https://mlsanity.com/paper/2305.03514/) (2023)
- [ChatGPT-4 Outperforms Experts and Crowd Workers in Annotating Political Twitter Messages with Zero-Shot Learning](https://mlsanity.com/paper/2304.06588/) (2023)
- [Investigating Data Contamination for Pre-training Language Models](https://mlsanity.com/paper/2401.06059/) (2024)
- [Language Model Fine-Tuning on Scaled Survey Data for Predicting Distributions of Public Opinions](https://mlsanity.com/paper/2502.16761/) (2025)
- [On the steerability of large language models toward data-driven personas](https://mlsanity.com/paper/2311.04978/) (2023)
- [Y Social: an LLM-powered Social Media Digital Twin](https://mlsanity.com/paper/2408.00818/) (2024)
- [CommunityLM: Probing Partisan Worldviews from Language Models](https://mlsanity.com/paper/2209.07065/) (2022)
- [Large Language Models as Subpopulation Representative Models: A Review](https://mlsanity.com/paper/2310.17888/) (2023)
- [COMMUNITY-CROSS-INSTRUCT: Unsupervised Instruction Generation for Aligning Large Language Models to Online Communities](https://mlsanity.com/paper/2406.12074/) (2024)
- [A Public Dataset Tracking Social Media Discourse about the 2024 U.S. Presidential Election on Twitter/X](https://mlsanity.com/paper/2411.00376/) (2024)
- [Pandemic Culture Wars: Partisan Differences in the Moral Language of COVID-19 Discussions](https://mlsanity.com/paper/2305.18533/) (2023)
- [On the rise of fear speech in online social media](https://mlsanity.com/paper/2303.10311/) (2023)
- [From Concepts to Components: Concept-Agnostic Attention Module Discovery in Transformers](https://mlsanity.com/paper/2506.17052/) (2025)
- [Fear and Loathing on the Frontline: Decoding the Language of Othering by Russia-Ukraine War Bloggers](https://mlsanity.com/paper/2409.13064/) (2024)
- [Bridging the Narrative Divide: Cross-Platform Discourse Networks in Fragmented Ecosystems](https://mlsanity.com/paper/2505.21729/) (2025)

## Abstract (arXiv)

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.