FutureGen: A RAG-based Approach to Generate the Future Work of Scientific Article
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912569858457600 |
|---|---|
| author | Azher, Ibrahim Al Mokarrama, Miftahul Jannat Guo, Zhishuai Choudhury, Sagnik Ray Alhoori, Hamed |
| author_facet | Azher, Ibrahim Al Mokarrama, Miftahul Jannat Guo, Zhishuai Choudhury, Sagnik Ray Alhoori, Hamed |
| contents | 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 a scientific article. To enrich the generation process with broader insights and reduce the chance of missing important research directions, we use context from related papers using RAG. We experimented with various Large Language Models (LLMs) integrated into Retrieval-Augmented Generation (RAG). We incorporate an LLM feedback mechanism to enhance the quality of the generated content and introduce an LLM-as-a-judge framework for robust evaluation, assessing key aspects such as novelty, hallucination, and feasibility. Our results demonstrate that the RAG-based approach using GPT-4o mini, combined with an LLM feedback mechanism, outperforms other methods based on both qualitative and quantitative evaluations. Moreover, we conduct a human evaluation to assess the LLM as an extractor, generator, and feedback provider. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_16561 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FutureGen: A RAG-based Approach to Generate the Future Work of Scientific Article Azher, Ibrahim Al Mokarrama, Miftahul Jannat Guo, Zhishuai Choudhury, Sagnik Ray Alhoori, Hamed Computation and Language Machine Learning 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 a scientific article. To enrich the generation process with broader insights and reduce the chance of missing important research directions, we use context from related papers using RAG. We experimented with various Large Language Models (LLMs) integrated into Retrieval-Augmented Generation (RAG). We incorporate an LLM feedback mechanism to enhance the quality of the generated content and introduce an LLM-as-a-judge framework for robust evaluation, assessing key aspects such as novelty, hallucination, and feasibility. Our results demonstrate that the RAG-based approach using GPT-4o mini, combined with an LLM feedback mechanism, outperforms other methods based on both qualitative and quantitative evaluations. Moreover, we conduct a human evaluation to assess the LLM as an extractor, generator, and feedback provider. |
| title | FutureGen: A RAG-based Approach to Generate the Future Work of Scientific Article |
| topic | Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2503.16561 |