Saved in:
Bibliographic Details
Main Author: Havlik, Denis
Format: Recurso digital
Language:
Published: Zenodo 2025
Online Access:https://doi.org/10.5281/zenodo.15101319
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • <p>This collection contains the results of four ClimEmpower / MAIA GenAI experiments. These experiments aim to asess how and to what extent the Generative AI models can help knowledge curators extract knowledge from documents they need to analyse. </p> <p>Concrete high-level research questions these experiments aim to resolve are:</p> <p><strong>RQ1: To what extent can the AI answers be used to formulate the final answers, without reading the whole document? </strong></p> <p><strong>RQ2: Which types of questions are easier or more difficult for GenAI models to answer?</strong></p> <p><strong>RQ3: How, and to what extent, can the answers be improved through prompt engineering? </strong></p> <p><strong>RQ4: To what extent do the GenAI models follow instructions to base the answers (only) on the content provided in the document?</strong></p> <p><strong>RQ5: How does the choice of GenAI model reflect in experiment results?</strong></p> <p>In addition, we were also interested in finding out the ways to further improve the SumQA, a Generative AI service that was developed in the MAIA project and supports batch-processing of documents.</p>