By providing INDUS with domain-specific vocabulary, the IMPACT-IBM team achieved superior performance over open, non-domain specific LLMs on a benchmark for biomedical tasks, a scientific question-answering benchmark, and Earth science entity recognition tests. By designing for diverse linguistic tasks and retrieval augmented generation, INDUS is able to process researcher questions, retrieve relevant documents, and generate answers to the questions. For latency sensitive applications, the team developed smaller, faster versions of both the encoder and sentence transformer models.
Related Posts
NASA Sets Briefings for Crew-8, International Space Station Missions
NASA will host a pair of news conferences Thursday, Jan. 25, from the agency’s Johnson Space Center in Houston to…
International SWOT Mission Can Improve Flood Prediction
Flooding on the Souris River inundated this community in North Dakota in 2011. The U.S.-French SWOT satellite is giving scientists…
From childhood stargazing to building a lunar space station
Even growing up in the heart of Washington, D.C., stargazer Oliver Ortiz felt a connection to space from a young…