The future work section of a scientific article outlines potential research directions by identifying gaps and limitations of a current study. This section serves as a valuable resource for early-career researchers seeking unexplored areas and experienced researchers looking for new projects or collaborations. In this study, we generate future work suggestions from key sections of a scientific article alongside related papers and analyze how the trends have evolved. We experimented with various Large Language Models (LLMs) and integrated Retrieval-Augmented Generation (RAG) to enhance the generation process. We incorporate a LLM feedback mechanism to improve the quality of the generated content and propose an LLM-as-a-judge approach for evaluation. Our results demonstrated that the RAG-based approach with LLM feedback outperforms other methods evaluated through qualitative and quantitative metrics. Moreover, we conduct a human evaluation to assess the LLM as an extractor and judge. The code and dataset for this project are here, code: HuggingFace
View on arXiv@article{azher2025_2503.16561,
title={ FutureGen: LLM-RAG Approach to Generate the Future Work of Scientific Article },
author={ Ibrahim Al Azher and Miftahul Jannat Mokarrama and Zhishuai Guo and Sagnik Ray Choudhury and Hamed Alhoori },
journal={arXiv preprint arXiv:2503.16561},
year={ 2025 }
}