Agam Goyal
@agam-goyal.bsky.social
CS PhD Student @illinoisCDS | Previously: BS Computer Science, Mathematics, and Data Science @UWMadison’24, 2x Intern @Amazon
Website: https://agoyal0512.github.io
Website: https://agoyal0512.github.io
Excited to be in Albuquerque for #NAACL2025 next week!
I'll be presenting our work on SLMs for governing online communities on 4pm Wednesday, April 30th in Oral Session D (CSS.1) in Room Ruidoso .
Come by if you’re interested in LLM for governance or computational modeling of online communities!
I'll be presenting our work on SLMs for governing online communities on 4pm Wednesday, April 30th in Oral Session D (CSS.1) in Room Ruidoso .
Come by if you’re interested in LLM for governance or computational modeling of online communities!
🚨 New #NAACL2025 paper alert: “SLM-Mod: Small Language Models Surpass LLMs at Content Moderation”
We show that fine-tuned small language models outperform LLMs like GPT-4o for content moderation tasks, with higher accuracy and recall!
🔗 arXiv: arxiv.org/pdf/2410.13155
🧵[1/7]
We show that fine-tuned small language models outperform LLMs like GPT-4o for content moderation tasks, with higher accuracy and recall!
🔗 arXiv: arxiv.org/pdf/2410.13155
🧵[1/7]
arxiv.org
April 25, 2025 at 8:38 PM
Excited to be in Albuquerque for #NAACL2025 next week!
I'll be presenting our work on SLMs for governing online communities on 4pm Wednesday, April 30th in Oral Session D (CSS.1) in Room Ruidoso .
Come by if you’re interested in LLM for governance or computational modeling of online communities!
I'll be presenting our work on SLMs for governing online communities on 4pm Wednesday, April 30th in Oral Session D (CSS.1) in Room Ruidoso .
Come by if you’re interested in LLM for governance or computational modeling of online communities!
🚨 New #NAACL2025 paper alert: “SLM-Mod: Small Language Models Surpass LLMs at Content Moderation”
We show that fine-tuned small language models outperform LLMs like GPT-4o for content moderation tasks, with higher accuracy and recall!
🔗 arXiv: arxiv.org/pdf/2410.13155
🧵[1/7]
We show that fine-tuned small language models outperform LLMs like GPT-4o for content moderation tasks, with higher accuracy and recall!
🔗 arXiv: arxiv.org/pdf/2410.13155
🧵[1/7]
arxiv.org
April 25, 2025 at 8:35 PM
🚨 New #NAACL2025 paper alert: “SLM-Mod: Small Language Models Surpass LLMs at Content Moderation”
We show that fine-tuned small language models outperform LLMs like GPT-4o for content moderation tasks, with higher accuracy and recall!
🔗 arXiv: arxiv.org/pdf/2410.13155
🧵[1/7]
We show that fine-tuned small language models outperform LLMs like GPT-4o for content moderation tasks, with higher accuracy and recall!
🔗 arXiv: arxiv.org/pdf/2410.13155
🧵[1/7]