Steps to Start:
- Go to z.umn.edu/QMRAbot and create an account by signing in with the checkbox "Create Account" checked.
- Go to the Account page. You can upload to “Local Database” the files that contain Basic Knowledge of your research field, such as review articles, your own papers, major references for your active projects, etc. It is not necessary for you to upload anything to the “OpenAI Database”. The default file in that database is a file recording useful information from your future conversations with the QMBot (“that database” can refer to either Local or OpenAI depending on where we decide to put it).
- Go to the Chat page to start a conversation.
- When you are done with a conversation, click Reset or close the tab. You will see a warning box that this action will clear information associated with the current conversation - click Confirm to exit.
How to Chat with the QMBot:
- You can ask the ChatBot to do a search on arXiv, e.g.: Get me recent 10 papers about superconducting materials from arXiv.
- Once the search is done, you will see the list of retrieved papers in the chatbox and also in the Retrieved Papers box. The numeric value shown next to each paper reflects its relevance to the Knowledge Base (files in Local Database). A lower value indicates higher relevance.
- Each retrieved paper in the chatbox typically has a clickable link that directs you to the paper or its arXiv abstract page. You can also click the title in the Retrieved Papers box to access a paper on the arXiv website.
- If you are interested in one or more papers and want to discuss their detailed contents, click on the Associate button next to the paper. The associated papers will appear in the Associated Papers box.
- In-depth questions you can ask the QMBot include: Look into the full text of the paper titled “xxx” and give me a summary; Go through the papers titled “xxx”, “yyy”, “zzz”, … and make a table summarizing all the transition temperatures of antiferromagnets mentioned.
- During the conversation, if you find some information that you want to add to your knowledge, you can say “Remember this”. The QMBot will record a summary of the conversation in a user preference document.
How the QMBot is Personalized:
- On the Account page, the Local Database contains files central to the user’s knowledge, which are used to calculate relevance scores for search results returned from arXiv.
- On the same page, the “OpenAI Database” contains files associated with the current conversation. You can ask detailed questions about these files.
- You can manually add papers to the OpenAI Database, allowing you to include familiar papers from previous work into the current conversation alongside new arXiv papers.
- The user preference document under the openAI and local databases registers your previous conversation with the ChatBot. Its content is also used to calculate relevance scores.
- The OpenAI database (excluding the user preference file) will be cleared if you close the tab, or log out/reset.