Paper Number

ICIS2025-2370

Paper Type

PDW

Abstract

After highlighting the strengths and limitations of current AI approaches, current corresponding solutions to support literature reviews will be presented. We will focus on solutions that are destined to an academic audience and we will compare them on dimensions such as system transparency, input data, user control, output presentation, functionality. Hybrid neuro-symbolic systems, which combine transparently logical reasoning for clustering literature with pattern recognition for synthesizing it will be introduced. The focus will then be ARTIREV (https://www.scanlitt.com/), a hybrid AI tool integrating a bibliometric expert system coupled with fine-tuned generative AI (SOCRATES) offering improved transparency, exhaustivity, and reliability. Attendees will experiment with ARTIREV to conduct, on the spot, a literature review on the subject of their choice. They will critically assess the capabilities of the proposed tool, while benchmarking it against any other AI solution of their choice.

Comments

27-PDW

Download

Share

COinS
 
Dec 14th, 12:00 AM

Trustworthy AI to conduct literature reviews

After highlighting the strengths and limitations of current AI approaches, current corresponding solutions to support literature reviews will be presented. We will focus on solutions that are destined to an academic audience and we will compare them on dimensions such as system transparency, input data, user control, output presentation, functionality. Hybrid neuro-symbolic systems, which combine transparently logical reasoning for clustering literature with pattern recognition for synthesizing it will be introduced. The focus will then be ARTIREV (https://www.scanlitt.com/), a hybrid AI tool integrating a bibliometric expert system coupled with fine-tuned generative AI (SOCRATES) offering improved transparency, exhaustivity, and reliability. Attendees will experiment with ARTIREV to conduct, on the spot, a literature review on the subject of their choice. They will critically assess the capabilities of the proposed tool, while benchmarking it against any other AI solution of their choice.

When commenting on articles, please be friendly, welcoming, respectful and abide by the AIS eLibrary Discussion Thread Code of Conduct posted here.