Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.15292 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909797167661056 |
|---|---|
| author | Dhakal, Abhiyan Paudel, Kausik Sigdel, Sanjog |
| author_facet | Dhakal, Abhiyan Paudel, Kausik Sigdel, Sanjog |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_15292 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | An Artificial Intelligence Driven Semantic Similarity-Based Pipeline for Rapid Literature Dhakal, Abhiyan Paudel, Kausik Sigdel, Sanjog Artificial Intelligence 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. |
| title | An Artificial Intelligence Driven Semantic Similarity-Based Pipeline for Rapid Literature |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2509.15292 |