Koustuv Saha — accepted AI-conference papers

2025

MoMoE: Mixture of Moderation Experts Framework for AI-Assisted Online Governance

Agam Goyal, Xianyang Zhan, Yilun Chen, Koustuv Saha, Eshwar Chandrasekharan

EMNLP 2025

Large language models (LLMs) have shown great potential in flagging harmful content in online communities. Yet, existing approaches for moderation require a separate model for every community and are opaque in their decision-making, limiting real-world adoption. We introduce Mixture of Moderation Ex

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2025

SLM-Mod: Small Language Models Surpass LLMs at Content Moderation

Xianyang Zhan, Agam Goyal, Yilun Chen, Eshwar Chandrasekharan, Koustuv Saha

NAACL 2025long

Large language models (LLMs) have shown promise in many natural language understanding tasks, including content moderation. However, these models can be expensive to query in real-time and do not allow for a community-specific approach to content moderation. To address these challenges, we explore t…

Cited by 2 Source ↗PDF ↗code ↗Scholar ↗