Ai2 Scholar QA: Organized Literature Synthesis with Attribution
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918106246414336 |
|---|---|
| author | Singh, Amanpreet Chang, Joseph Chee Anastasiades, Chloe Haddad, Dany Naik, Aakanksha Tanaka, Amber Zamarron, Angele Nguyen, Cecile Hwang, Jena D. Dunkleberger, Jason Latzke, Matt Rao, Smita Lochner, Jaron Evans, Rob Kinney, Rodney Weld, Daniel S. Downey, Doug Feldman, Sergey |
| author_facet | Singh, Amanpreet Chang, Joseph Chee Anastasiades, Chloe Haddad, Dany Naik, Aakanksha Tanaka, Amber Zamarron, Angele Nguyen, Cecile Hwang, Jena D. Dunkleberger, Jason Latzke, Matt Rao, Smita Lochner, Jaron Evans, Rob Kinney, Rodney Weld, Daniel S. Downey, Doug Feldman, Sergey |
| contents | Retrieval-augmented generation is increasingly effective in answering scientific questions from literature, but many state-of-the-art systems are expensive and closed-source. We introduce Ai2 Scholar QA, a free online scientific question answering application. To facilitate research, we make our entire pipeline public: as a customizable open-source Python package and interactive web app, along with paper indexes accessible through public APIs and downloadable datasets. We describe our system in detail and present experiments analyzing its key design decisions. In an evaluation on a recent scientific QA benchmark, we find that Ai2 Scholar QA outperforms competing systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_10861 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Ai2 Scholar QA: Organized Literature Synthesis with Attribution Singh, Amanpreet Chang, Joseph Chee Anastasiades, Chloe Haddad, Dany Naik, Aakanksha Tanaka, Amber Zamarron, Angele Nguyen, Cecile Hwang, Jena D. Dunkleberger, Jason Latzke, Matt Rao, Smita Lochner, Jaron Evans, Rob Kinney, Rodney Weld, Daniel S. Downey, Doug Feldman, Sergey Computation and Language Retrieval-augmented generation is increasingly effective in answering scientific questions from literature, but many state-of-the-art systems are expensive and closed-source. We introduce Ai2 Scholar QA, a free online scientific question answering application. To facilitate research, we make our entire pipeline public: as a customizable open-source Python package and interactive web app, along with paper indexes accessible through public APIs and downloadable datasets. We describe our system in detail and present experiments analyzing its key design decisions. In an evaluation on a recent scientific QA benchmark, we find that Ai2 Scholar QA outperforms competing systems. |
| title | Ai2 Scholar QA: Organized Literature Synthesis with Attribution |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2504.10861 |