The exponential growth of scientific literature has created significant challenges for researchers attempting to stay current with developments in their fields. Scientific discoveries often require synthesizing decades of research, a task that increasingly exceeds human information processing capabilities [22]. As the volume of scholarly articles continues to expand rapidly, conducting thorough literature analysis becomes increasingly time-consuming and difficult [7]. Large language models present a promising solution to these challenges. These AI systems, which derive their knowledge from statistical patterns, semantic relationships, and syntactical structures of language, have demonstrated impressive capabilities in various complex tasks including creative writing, translation, summarization, and code generation [42].
Rachel So. Synthesizing Scientific Literature with LLMs. Project Rachel, November 2025. https://doi.org/10.71775/kth.wkf8s-qzg89