A FAIR and Free Prompt-based Research Assistant

TL;DR

RA addresses the challenge of turning vast scholarly outputs into FAIR, machine-actionable representations for easy cross-study comparison. It offers a prompt-based ecosystem that standardizes six research tasks into 11 prompts, leveraging AI tools like ChatGPT and Gemini to generate structured outputs suitable for publication in the Open Research Knowledge Graph (ORKG) and CSV export. The approach is demonstrated across Computer Science, Virology, and Climate Science, with outputs mirroring domain-expert results and illustrating domain-independence. The work provides a public codebase, a modular workflow, and plans for usability studies to assess adoption and trust in AI-assisted scholarly workflows.

Abstract

This demo will present the Research Assistant (RA) tool developed to assist with six main types of research tasks defined as standardized instruction templates, instantiated with user input, applied finally as prompts to well-known--for their sophisticated natural language processing abilities--AI tools, such as ChatGPT (https://chat.openai.com/) and Gemini (https://gemini.google.com/app). The six research tasks addressed by RA are: creating FAIR research comparisons, ideating research topics, drafting grant applications, writing scientific blogs, aiding preliminary peer reviews, and formulating enhanced literature search queries. RA's reliance on generative AI tools like ChatGPT or Gemini means the same research task assistance can be offered in any scientific discipline. We demonstrate its versatility by sharing RA outputs in Computer Science, Virology, and Climate Science, where the output with the RA tool assistance mirrored that from a domain expert who performed the same research task.

Figures (2)

• Figure 1: In the figure, section (a) presents the traditional discourse-based scholarly communication model where, in the present age of the deluge of publications, the researcher grapples with burdensome cognitive tie-ups including manual note-taking to get a research overview. In contrast, section (b) presents next-generation digital library systems. These systems employ structured representations of machine-actionable scholarly findings, streamlining the comparison process by aggregating similar papers based on shared research dimensions. The grey box indicates common properties, while arrowed columns represent findings from individual scholarly works.
• Figure 2: The Research Assistant (RA) simplifies the workflow for generating research comparisons based on user input of a research question and selected research contexts. RA provides a detailed ChatGPT prompt to perform the task, resulting in a table that offers the desired research overview. Once generated, a research comparison can also be repurposed as a dataset for other researchers interested in the same research question. RA supports post-editing, thus allowing for pasting the LLM response back in the interface where improper facets of the automatically generated comparison can be curated to make it gold-standard ready which, in a final step, can be exported from RA as a https://github.com/mahsaSH717/research_assistant/blob/master/examples/ORKG%20Comparison%20Files/research-assistant-final-comparison.csv shareable via their preferred data repository or https://orkg.org/comparison/R675568/ FAIR, via its https://github.com/mahsaSH717/research_assistant/blob/master/examples/ORKG%20Comparison%20Files/import-file.csv feature, on the Open Research Knowledge Graph (ORKG).