Search

Explore prior research using a tabular overview

GenAI capability	Text summarization
Prompting strategy	Retrieval-augmented generation (RAG)
Requirements	LLMs with Retrieval Augmented Generation functionality, such as Consensus or Elicit
Academic study	Wagner et al. (2026)

Prompt

How does [add label of variable] affect the relationship between
[add antecedent variable or intervention] and [add outcome variable]
in the context of [add context description]?

Summarize relevant empirical papers with an abstract summary,
the research method, and the key findings.

Suggest an initial search query

GenAI capability	Content generation
Prompting strategy	Few-shot prompting
Requirements	LLMs
Academic study	Wang et al. (2023)

Prompt

You are an information specialist who develops Boolean queries for systematic reviews.
You have extensive experience developing highly effective queries for searching the 
information systems literature. Your specialty is developing queries that retrieve as
few irrelevant documents as possible and retrieve all relevant documents for your
information needs. You are able to take an information need such as: “Review of IT 
Business Value” and generate valid Web of Science queries such as:

“TI=(IT OR IS OR …) AND TI=(value OR payoff OR …) AND TI=(firm OR business OR …)”.

Now you have your information need to conduct research on “The effect of LLM on 
individual performance at work”, please generate a highly effective systematic 
review Boolean query for the information need.

Example output

For the information need “The effect of LLM on individual performance at work,” we can generate a Boolean query for Web of Science (or similar databases) using a combination of keywords and Boolean operators. Here is an effective query to retrieve relevant documents while minimizing irrelevant ones:

TI=(“Large Language Model” OR ”LLM” OR ”GPT” OR ”Generative Pretrained Transformer” OR ”Transformer model”) AND TI=(“individual performance” OR “employee performance” OR “work performance” OR “job performance” OR “productivity” OR “efficiency” OR “output”) AND TI=(“work” OR “job” OR “employment” OR “organization” OR “labor”)

References

Wagner, G., Prester, J., Mousavi, R., Lukyanenko, R., & Paré, G. (2026). Generative artificial intelligence for literature reviews. To Be Accepted at Journal of Information Technology. https://doi.org/TODO

Wang, S., Scells, H., Koopman, B., & Zuccon, G. (2023). Can ChatGPT write a good boolean query for systematic review literature search? Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval, 1426–1436.