Patrick Gerard

Patrick Gerard, William Theisen, Tim Weninger et al.

Othering, the act of portraying outgroups as fundamentally different from the ingroup, often escalates into framing them as existential threats--fueling intergroup conflict and justifying exclusion and violence. These dynamics are alarmingly pervasive, spanning from the extreme historical examples of genocides against minorities in Germany and Rwanda to the ongoing violence and rhetoric targeting migrants in the US and Europe. While concepts like hate speech and fear speech have been explored in existing literature, they capture only part of this broader and more nuanced dynamic which can often be harder to detect, particularly in online speech and propaganda. To address this challenge, we introduce a novel computational framework that leverages large language models (LLMs) to quantify othering across diverse contexts, extending beyond traditional linguistic indicators of hostility. Applying the model to real-world data from Telegram war bloggers and political discussions on Gab reveals how othering escalates during conflicts, interacts with moral language, and garners significant attention, particularly during periods of crisis. Our framework, designed to offer deeper insights into othering dynamics, combines with a rapid adaptation process to provide essential tools for mitigating othering's adverse impacts on social cohesion.

Patrick Gerard, Svitlana Volkova, Louis Penafiel et al.

Following the Russian Federation's full-scale invasion of Ukraine in February 2022, a multitude of information narratives emerged within both pro-Russian and pro-Ukrainian communities online. As the conflict progresses, so too do the information narratives, constantly adapting and influencing local and global community perceptions and attitudes. This dynamic nature of the evolving information environment (IE) underscores a critical need to fully discern how narratives evolve and affect online communities. Existing research, however, often fails to capture information narrative evolution, overlooking both the fluid nature of narratives and the internal mechanisms that drive their evolution. Recognizing this, we introduce a novel approach designed to both model narrative evolution and uncover the underlying mechanisms driving them. In this work we perform a comparative discourse analysis across communities on Telegram covering the initial three months following the invasion. First, we uncover substantial disparities in narratives and perceptions between pro-Russian and pro-Ukrainian communities. Then, we probe deeper into prevalent narratives of each group, identifying key themes and examining the underlying mechanisms fueling their evolution. Finally, we explore influences and factors that may shape the development and spread of narratives.

Patrick Gerard, Svitlana Volkova

Language models deployed in online communities must adapt to norms that vary across social, cultural, and domain-specific contexts. Prior alignment approaches rely on explicit preference supervision or predefined principles, which are effective for well-resourced settings but exclude most online communities -- particularly those without institutional backing, annotation infrastructure, or organized around sensitive topics -- where preference elicitation is costly, ethically fraught, or culturally misaligned. We observe that communities already express preferences implicitly through what content they accept, engage with, and allow to persist. We show that this acceptance behavior induces measurable geometric structure in representation space: accepted responses occupy coherent, high-density regions that reflect community-specific norms, while rejected content falls in sparser or misaligned areas. We operationalize this structure as an implicit preference signal for alignment and introduce density-guided response optimization (DGRO), a method that aligns language models to community norms without requiring explicit preference labels. Using labeled preference data, we demonstrate that local density recovers pairwise community judgments, indicating that geometric structure encodes meaningful preference signal. We then apply DGRO in annotation-scarce settings across diverse communities spanning platform, topic, and language. DGRO-aligned models consistently produce responses preferred by human annotators, domain experts, and model-based judges over supervised and prompt-based baselines. We position DGRO as a practical alignment alternative for communities where explicit preference supervision is unavailable or misaligned with situated practices, and discuss the implications and risks of learning from emergent acceptance behavior.