From the source
LG AI Research announces the QASA approach and benchmark for scientific question answering, which decomposes QA into three sub-tasks and uses instruction-tuned LLMs.
From the source
From the source

LG AI Research announces the QASA approach and benchmark for scientific question answering, which decomposes QA into three sub-tasks and uses instruction-tuned LLMs.
From the source
LG AI Research proposes the advanced question answering on scientific articles (QASA) approach and benchmark for reasoning on scientific questions [8].
lgresearch.ai