2025.naacl-long.441.pdf

N/A

SLM-Mod: Small Language Models Surpass LLMs at Content Moderation Xianyang Zhan∗ , Agam Goyal∗ , Yilun Chen, Eshwar Chandrasekharan‡ , Koustuv Saha‡ Siebel School of Computing and Data Science University of Illinois Urbana-Champaign {zhan39, agamg2, yilunc3, eshwar, ksaha2}@illinois.edu Abstract Large language models (LLMs) have shown promise in many natural language understand-…

saved by

• Maisha Thasin

related reading

• LLM-Mod: Can Large Language Models Assist Content Moderation?koustuv.com
• Legilimens: Practical and Unified Content Moderation forLarge Language Model Servicesarxiv.org
• RigorLLM: Resilient Guardrails for Large Language Models against Undesired Contentarxiv.org
• 2312.06674arxiv.org
• What We’ve Learned From A Year of Building with LLMs – Applied LLMsapplied-llms.org
• Patterns for Building LLM-based Systems & Productseugeneyan.com
• Little Free Language Modelswritefutureslab.com
• The Llama Hitchiking Guide to Local LLMs – hackerllamaosanseviero.github.io
• Things we learned about LLMs in 2024simonwillison.net
• Productizing Large Language Modelsblog.replit.com
• 2025: The year in LLMssimonwillison.net
• The bitter lesson of LLM evalsparsed.com