A Systematic Review of Prompt Engineering Paradigms in Organic Chemistry: Mining, Prediction, and Model Architectures

Large language models (LLMs) have emerged as transformative tools in scientific research, offering a powerful alternative to traditional, resource-intensive machine learning methods. By leveraging the vast knowledge encoded during pre-training, prompt engineering—the systematic design and optimization of input instructions—enables researchers to guide LLMs toward accurate and domain-specific outputs without updating model parameters. This review presents the first systematic examination of prompt engineering techniques within organic chemistry, focusing on two critical application areas: text mining and predictive tasks. We analyze the core paradigms of prompt engineering, including prompt design, prompt learning, and prompt tuning, and clarify terminological inconsistencies in the literature. The discussion is contextualized within the three principal LLM architectures (encoder-only, decoder-only, and encoder-decoder), with an evaluation of their respective performances on chemistry-related tasks. We searched Web of Science (WoS) and ChemRxiv from December 19 to December 25, 2025. A comprehensive search strategy was employed, combining keywords for prompt engineering and organic chemistry. Two reviewers independently screened titles, abstracts, and full texts against predefined eligibility criteria: primary focus on prompt engineering, use of at least one LLM, and direct relevance to organic chemistry (particularly synthesis). Disagreements were resolved through consensus. Study characteristics and findings were extracted and synthesized narratively. From 101 identified records (WoS=70, ChemRxiv=31), 58 advanced to full-text review, yielding 22 studies for final inclusion (WoS=16, ChemRxiv=5, plus 1 via citation tracking). This review highlights the significant potential of LLM-driven prompt engineering to accelerate discovery in organic chemistry, from synthetic pathway optimization to automated literature analysis, while also addressing persistent challenges such as the limitations associated with various prompt engineering techniques and the constraints related to each sub-task.