Note: Ai2 is also the provider of the wonderful Semantic Scholar database. The new research tool discussed below (Paper Finder0 is free to access. Btw, today’s announcement follows a couple of related news items (more research tools) from Ai2. The posts from Jan. 2025 and Nov. 2024 are also linked at the bottom of this post.
Today we release Ai2 Paper Finder, an LLM-powered literature search system.
We believe that AI-based literature search should follow the research and thought process that a human researcher would use when looking for relevant papers in their field. Ai2 Paper Finder is built on this philosophy, and it excels at locating papers that are hard to find using existing search tools.
Consider your own research process and how you search for papers. For example, imagine you’re looking for papers that introduce a dataset of an unscripted dialogue between 2 speakers (written or transcription) in English where there is an annotation of some property (emotion, age, gender, etc.) of one of the speakers.
How would you approach it today?
You’ll likely start by choosing a tool, either Semantic Scholar, Google Scholar, or a regular Google search, or ask an LLM like GPT. You will then come up with search terms (based on your knowledge of both the domain and the tool you chose), and see what comes up. The results will likely not perfectly match what you need, but will be a good start. From the search results, your intuition will guide you to more follow-ups: maybe you learn new vocabulary or are reminded of a related concept that leads you to a new search query, or you find a promising lead and start to follow citations or a specific author’s work. The point is that literature search is a multi-step process that involves learning and iterating as you go.
We built this thinking process right into Ai2 Paper Finder. When you enter a query, you can watch as the system breaks down your query into relevant components, searches for papers, follows citations, evaluates for relevance, runs follow-up queries based on the results, and then presents not only the papers, but also short summaries of why the paper is relevant to your specific query.
Ai2 Paper Finder doesn’t need you to simplify your queries into keywords to perform an effective search, like that original example we started with, which we can enter into Paper Finder as-written, “papers that introduce a dataset of an unscripted dialogue between 2 speakers (written or transcription) in English where there is an annotation of some property (emotion, age, gender, etc..) of one of the speakers.”
Part of Ai2 Paper Finders reasoning process while it searches a query. Source: Ai2
[Clip]
We are excited to share the first iteration of Ai2 Paper Finder with the community. This is a work in progress, and we look forward to having everyone interact with it, use it for day-to-day work, and provide feedback on the results. Please try it out, explore its boundaries, and let us know if it doesn’t work as expected! We understand that Ai2 Paper Finder is far from perfect and we will actively monitor your feedback and look for opportunities to improve.
Paperfinder Vs Other Tools
How does Ai2 Paper Finder differ from other literature search solutions? First and foremost, we aim to be as open as possible. We are very interested in the research questions that openness enables, and we are committed to fully and openly describing every aspect of the system. To that end, a detailed tech report is coming soon. We also aim to be open about the query stream we receive, which, pending users’ opting in, we plan to mine for interesting queries and release as community-wide benchmarks. While issues relating to academic copyright complicate the process of open-sourcing the code today, we hope our commitment to openness will empower the rest of the community to join us in tackling big research questions, and we plan to release more of our source code in the future.
Other efforts (including Ai2 ScholarQA) are creating research summaries. Summaries are based on retrieval, but are different from paper finding. The difference is both in the form in which the results are presented (a list or a summary) but also on how the information is intended to be consumed. Summaries are meant as overviews, and are not meant to be exhaustive: if you get one prominent paper from an area, it is OK to neglect others. While in paper finding, we often want our results to be significantly more exhaustive. While summaries are mostly intended to learn about a new topic, paper finding helps you dig deeper into areas you already know.
Gary Price (gprice@gmail.com) is a librarian, writer, consultant, and frequent conference speaker based in the Washington D.C. metro area.
He earned his MLIS degree from Wayne State University in Detroit.
Price has won several awards including the SLA Innovations in Technology Award and Alumnus of the Year from the Wayne St. University Library and Information Science Program. From 2006-2009 he was Director of Online Information Services at Ask.com.
