ChemDataWriter: a transformer-based toolkit for auto-generating books that summarise research

Abstract

ChemDataWriter automatically generates literature reviews via artificial intelligence that suggests potential book content, by retrieving and re-ranking relevant papers that the user has provided as input, and summarising and paraphrasing the text within these papers.

Implementation and Evaluation of a ChatGPT-Assisted Special Topics Writing Assignment in Biochemistry

“…Therefore, GenAI tools that facilitate the retrieval and analysis of scientific literature in chemical research contexts could be more impactful in advanced undergraduate or graduate instructional settings than in undergraduate courses. Indeed, LLM-containing systems have demonstrated the ability to construct lengthy summaries of user-defined chemical research collections, while GPTs have been used to curate synthetic parameters for metal–organic frameworks (MOFs) from precompiled literature . Synthetic conditions for MOFs have also been optimized via LLM interfaces that possess basic experimental design and analysis capabilities. , Remarkably, an LLM-containing architecture that integrates these functions with robotic equipment manipulation has achieved self-driven organic syntheses and refinement of cross-coupling reaction conditions .…”