Showing cs.AIShow all
2 papers · 1 filter
cs.AI2025
OmniScience: A Domain-Specialized LLM for Scientific Reasoning and Discovery
Vignesh Prabhakar, Md Amirul Islam, Adam Atanas +8
Large Language Models (LLMs) have demonstrated remarkable potential in advancing scientific knowledge and addressing complex challenges. In this work, we introduce OmniScience, a s…
cs.AI2025
A Modular Dataset to Demonstrate LLM Abstraction Capability
Adam Atanas, Kai Liu
Large language models (LLMs) exhibit impressive capabilities but struggle with reasoning errors due to hallucinations and flawed logic. To investigate their internal representation…