Reproduce “An LLM-Powered Semantic Alignment Framework for Journal Recommendation” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Yanglin Yan, Zicheng Xie, Tianchen Gao, Rui Pan, Hansheng Wang
An LLM-powered semantic alignment framework facilitates journal recommendation by inferring journal suitability from manuscript content and journal scope descriptions in a zero-shot setting. The framework achieved a Top-3 accuracy of 40.23% on a dataset of 23,609 articles and provided interpretable reasoning for its suggestions.
Key insights
- Large language models can effectively perform journal recommendation in a zero-shot setting by directly inferring suitability from textual descriptions, bypassing task-specific training.
- The inclusion of reference information can enhance recommendation accuracy for many journals by providing a richer academic context, although its impact varies depending on the journal's scope.
- The LLM-powered framework generates largely stable recommendations and provides interpretable, structured reasoning, fostering user trust and aiding decision-making.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.