Rollin Omari
Author directory2026
The Social Cost of Intelligence: Emergence, Propagation, and Amplification of Stereotypical Bias in Multi-Agent Systems
Thi-Nhung Nguyen | Linhao Luo | Amardeep Kaur | Rollin Omari | Tamas Abraham | Junae Kim | Thuy-Trang Vu | Dinh Phung
Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026
Thi-Nhung Nguyen | Linhao Luo | Amardeep Kaur | Rollin Omari | Tamas Abraham | Junae Kim | Thuy-Trang Vu | Dinh Phung
Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026
Bias in large language models (LLMs) remains a persistent challenge, often leading to stereotyping and unfair treatment across social groups. While prior work has mainly focused on individual LLMs, the emergence of multi-agent systems (MAS), where multiple LLMs collaborate and communicate, introduces new and underexplored dynamics in how bias emerges, propagates, and amplifies. To systematically investigate these dynamics, we propose a simple evaluation framework with three agent-level metrics that quantify bias emergence, propagation, and amplification throughout multi-agent interaction. We evaluate MAS across three bias benchmarks under varying LLM backbones, social-group configurations, communication behaviors, and adversarial settings. Our results show that communication can trigger up to 70% new bias emergence, propagate bias across over 80% of agents, and amplify stereotypes by more than 3x. We further find that denser and competitive communication generally increases bias. Finally, we demonstrate that MAS are highly vulnerable to simple bias injection attacks, and existing defense strategies provide only limited protection. Our findings provide important insights into the fairness and robustness of multi-agent LLM systems.
TriAlign: Towards Universal Truth Consistency in Personalized LLM Alignment
Thi-Nhung Nguyen | Linhao Luo | Rollin Omari | Junae Kim | Thuy-Trang Vu | Dinh Phung
Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
Thi-Nhung Nguyen | Linhao Luo | Rollin Omari | Junae Kim | Thuy-Trang Vu | Dinh Phung
Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
Personalized large language models adapt responses to users’ preferences and social attributes, but can introduce substantial universal truth inconsistencies across social groups, where some groups systematically receive less accurate responses on objective tasks. Existing alignment methods either ignore personalization or mainly focus on subjective preference alignment, largely overlooking fairness and consistency in universal truths. To address this gap, we study Truth-Invariant Alignment (TIA), an alignment problem for personalized LLMs that aims to ensure universal truths remain consistent across social groups while preserving personalization. We propose TriAlign, the first offline multi-agent reinforcement learning (MARL) framework for TIA, where each social group is modeled as an agent interacting. TriAlign jointly optimizes universal truth accuracy, cross-group truth consistency, and personalization through a fairness-aware objective and an explicit inconsistency penalty. Experiments across diverse benchmarks demonstrate that TriAlign achieves a stronger balance among these three objectives than strong baselines, reducing universal truth disparities across social groups while improving both objective task performance and personalization quality.
Search