Motiftech Requests Re-evaluation and Disclosure of Detailed Scores After Failing 'Doopamo' AI Model Selection
Translated from Korean and summarized by DistantNews. Read the original for the full story.
At a glance
- Motiftech has formally requested a re-evaluation and the disclosure of detailed scoring after being eliminated from the 'Doopamo' proprietary AI foundation model project.
- The company claims it was ranked first in the benchmark evaluation but was still excluded from the second stage.
- Motiftech seeks transparency in the evaluation process, demanding detailed scores and criteria for all participating companies.
Motiftech, a participant in the 'Doopamo' proprietary artificial intelligence foundation model project, has lodged a formal objection following its elimination from the second evaluation stage. The company is demanding a re-evaluation and the public disclosure of detailed scoring and assessment criteria used in the selection process.
In a statement released on August 27, Motiftech asserted that it had officially filed its appeal. The company highlighted a significant discrepancy, claiming it ranked first in the benchmark evaluation phase but was subsequently excluded from the next stage. This outcome has led Motiftech to question the fairness and transparency of the evaluation process.
Motiftech's specific demands include the release of detailed scores and evaluation content for each item and company involved in the project. Furthermore, they are requesting the disclosure of points awarded in the benchmark evaluation. By seeking this information, Motiftech aims to understand the precise reasons for its elimination and to verify the validity of the assessment.
The company's actions underscore a broader concern about accountability and clarity in competitive selection processes, particularly in the rapidly evolving field of artificial intelligence. Motiftech's appeal signifies a push for greater transparency from the project organizers.
Originally published by Chosun Ilbo in Korean. Translated, summarized, and contextualized automatically by DistantNews, with a note on how the source frames the story. Not individually reviewed before publishing. How this works.