An Artificial Intelligence Driven Semantic Similarity-Based Pipeline for Rapid Literature
This provides a practical, low-overhead tool for researchers conducting literature reviews, but it is incremental as it builds on existing semantic similarity methods without major breakthroughs.
The authors tackled the problem of automating literature reviews by developing a pipeline that uses transformer embeddings and cosine similarity to fetch and rank relevant papers from open access repositories based on semantic closeness to an input title and abstract. The system shows promise as a scalable tool for preliminary research, though it lacks heuristic feedback or ground truth validation.
We propose an automated pipeline for performing literature reviews using semantic similarity. Unlike traditional systematic review systems or optimization based methods, this work emphasizes minimal overhead and high relevance by using transformer based embeddings and cosine similarity. By providing a paper title and abstract, it generates relevant keywords, fetches relevant papers from open access repository, and ranks them based on their semantic closeness to the input. Three embedding models were evaluated. A statistical thresholding approach is then applied to filter relevant papers, enabling an effective literature review pipeline. Despite the absence of heuristic feedback or ground truth relevance labels, the proposed system shows promise as a scalable and practical tool for preliminary research and exploratory analysis.