Ethical Tech CoLab · Fall 2025 Cohort
A survey of how AI helps researchers move from a broad area of interest to a well-formed, answerable research question — and the guardrails that responsible use demands.
The paper surveys where AI genuinely helps across a researcher's workflow — from scouting the literature to drafting a candidate question.
NLP gap finders (GapFinder), keyword co-occurrence graphs, and knowledge-graph analysis surface topics that remain under-investigated.
Systems like SCIMUSE (a 58M-paper graph plus GPT-4) and AGATHA generate candidate questions — about 25% of SCIMUSE's ideas were rated highly interesting by expert reviewers.
Tools like Elicit, Scispace, and Consensus condense the literature so a new question is grounded in what is already known.
Scite and NLP contradiction detectors expose disagreements in the literature — often the most productive place to pose a question.
End-to-end platforms combine search, summarization, and suggestion into one interactive workflow.
The same generative power that suggests high-value questions can hallucinate citations, fabricate conceptual links, or overstate consensus. Responsible use asks researchers to:
The paper, plus the practical materials it ships with.
All eight sections, from gap identification through conflict-of-interest detection, with a comparison of AI tools.
Read →A reusable prompt, ready to paste into Microsoft Copilot's Researcher tool or any LLM session.
Copy the prompt →An example 1–5 rubric for scoring how peer-reviewed and trustworthy a journal is.
See the rubric →