Feedback-aligned Mixed LLMs for Machine Language-Molecule Translation

arXiv:2405.13984v1 Announce Type: new
Abstract: The intersection of chemistry and Artificial Intelligence (AI) is an active area of research focused on accelerating scientific discovery. While using large language models (LLMs) with scientific modalities has shown potential, there are significant challenges to address, such as improving training efficiency and dealing with the out-of-distribution problem. Focussing on the task of automated language-molecule translation, we are the first to use state-of-the art (SOTA) human-centric optimisation algorithms in the cross-modal setting, successfully aligning cross-language-molecule …

abstract artificial artificial intelligence arxiv challenges chemistry cs.cl cs.mm discovery distribution efficiency feedback improving intelligence intersection language language models large language large language models llms machine mixed potential research scientific scientific discovery training translation type while