Large language model (LLM) agents are increasingly acting as human delegates in multiagent environments, where a representative agent integrates diverse peer perspectives to make a final decision.Drawing inspiration from social psychology, we investigate how the reliability of this representative agent is undermined by the social context of its network.We define four key phenomena-social conformity, perceived expertise, dominant speaker effect, and rhetorical persuasion-and systematically manipulate the number of adversaries, relative intelligence, argument length, and argumentative styles.Our experiments demonstrate that the representative agent's accuracy consistently declines as social pressure increases: larger adversarial groups, more capable peers, and longer arguments all lead to significant performance degradation.Furthermore, rhetorical strategies emphasizing credibility or logic can further sway the agent's judgment, depending on the context.These findings reveal that multiagent systems are sensitive not only to individual reasoning but also to the social dynamics of their configuration, highlighting critical vulnerabilities in AI delegates that mirror the psychological biases observed in human group decision-making.

Static benchmarks for harmful content detection face limitations in scalability and diversity, and may also be affected by contamination from web-scale pre-training corpora.To address these issues, we propose a framework for synthesizing harmful content, leveraging persona-guided large language model (LLM) agents.Our approach constructs twodimensional user personas by integrating demographic identities and topical interests with situational harmful strategies, enabling the simulation of diverse and contextually grounded harmful interactions.We evaluate the framework along three dimensions: harmfulness, challenge level, and diversity.Both human and LLM-based evaluations confirm that our framework achieves a high harmful generation success rate.Experiments across multiple detection systems reveal that our synthetic scenarios are more challenging to detect than those in existing benchmarks.Furthermore, a multifaceted analysis confirms that our approach achieves linguistic and topical diversity comparable to human-curated datasets, establishing our framework as an effective tool for robust stress-testing of harmful content detection systems 1 .

Content moderation research has recently made significant advances, but remains limited in serving the majority of the world's languages due to the lack of resources, leaving millions of vulnerable users to online hostility. This work presents a large-scale human-annotated multi-task benchmark dataset for abusive language detection in Tigrinya social media with joint annotations for three tasks: abusiveness, sentiment, and topic classification. The dataset comprises 13,717 YouTube comments annotated by nine native speakers, collected from 7,373 videos with a total of over 1.2 billion views across 51 channels. We developed an iterative term clustering approach for effective data selection. Recognizing that around 64% of Tigrinya social media content uses Romanized transliterations rather than native Ge'ez script, our dataset accommodates both writing systems to reflect actual language use. We establish strong baselines across the tasks in the benchmark, while leaving significant challenges for future contributions. Our experiments demonstrate that small fine-tuned models outperform prompted frontier large language models (LLMs) in the low-resource setting, achieving 86.67% F1 in abusiveness detection (7+ points over best LLM), and maintain stronger performance in all other tasks. The benchmark is made public to promote research on online safety.