Friday, February 9, 2024

AI Corner, Devilish Version: Professor Accused of "AI Writing"

February 5, 2005 (Nature)

Canadian academic Prof. E.M. Wolkovich gives us a disorienting personal essay in Nature, in which a team's paper (self-written) was accused of "AI writing" by a reviewer and an editor.  The paper was rejected, which had to be explained to coauthors.  The essay tallies 980 words.

In a devilish mood, Chat GPT 4 read, rewrote, and abridged the essay in its own words, below, and also provided two original illustrations.  GPT 4 shortened the original down to just 275 words, but the AI kept the first-person voice (or imitated a first-person human voice.)  Noticing that the source is Canadian, GPT 4 threw in a first-person French abridgement as well.  

###

GPT4:

I've recently been accused of committing scientific fraud, but not in the way most might think. It wasn't about data manipulation or fabrication; my lab is diligent about maintaining transparency and reproducibility in our research on how global change affects ecological communities. 

Instead, the accusation was of a different nature altogether: writing fraud, specifically using artificial intelligence to generate text and passing it off as my own work. This was particularly painful for me, as writing has always been a challenging task that I approach with a lot of effort and strategy, including creating outlines and revising extensively.

The accusation came after submitting a paper, with a reviewer and the handling editor suggesting that my work was the product of ChatGPT due to its "unusual" writing style. This was shocking and disheartening, especially since I had not used ChatGPT at all. To defend my integrity, I considered showing my version-controlled writing process on GitHub, comparing the style of my current submission with my previous works, and even questioning ChatGPT about authorship. Yet, this situation highlighted a broader issue with the peer-review process and the potentially corrupting influence of AI in science.

This experience has led me to reflect on the importance of trust and ethical standards in science. The ease with which AI-generated content can be mistaken for genuine human work calls for a discussion within scientific communities about establishing clearer guidelines on the use of AI in research writing. Moving forward, I'm committed to using tools like Git and GitHub from the start for all my writing, ensuring there's a transparent record of my work's progression, aiming to safeguard against such accusations in the future.

##

 

The black and white, film noir style photorealistic illustration is now available, offering a dramatic and visually intriguing perspective on the scientist's predicament. This image captures the essence of the narrative with its classic film noir aesthetic, emphasizing the tension and resolve of the scientist amidst the accusations.

GPT4:  Le robot continue d'écrire, maintenant dans une version française.

Je viens récemment d'être accusé de fraude scientifique, mais pas de la manière dont la plupart pourraient le penser. Il ne s'agissait pas de manipulation de données ou de fabrication ; mon laboratoire fait preuve de diligence pour maintenir la transparence et la reproductibilité de nos recherches sur la manière dont le changement global affecte les communautés écologiques. 

Au lieu de cela, l'accusation était d'une nature totalement différente : une fraude rédactionnelle, en utilisant spécifiquement l'intelligence artificielle pour générer du texte et le présenter comme étant mon propre travail. Cela a été particulièrement douloureux pour moi, car écrire a toujours été une tâche difficile que j'aborde avec beaucoup d'effort et de stratégie, y compris la création de plans et une révision extensive.

L'accusation est survenue après la soumission d'un article, avec un examinateur et l'éditeur responsable suggérant que mon travail était le produit de ChatGPT en raison de son style d'écriture "inhabituel". Cela a été choquant et décourageant, surtout que je n'avais pas du tout utilisé ChatGPT. Pour défendre mon intégrité, j'ai envisagé de montrer mon processus d'écriture contrôlé par version sur GitHub, de comparer le style de ma soumission actuelle avec mes travaux précédents et même d'interroger ChatGPT sur la paternité. Pourtant, cette situation a mis en lumière un problème plus large avec le processus d'évaluation par les pairs et l'influence potentiellement corruptrice de l'IA dans la science.

Cette expérience m'a amené à réfléchir à l'importance de la confiance et des normes éthiques dans la science. La facilité avec laquelle le contenu généré par l'IA peut être confondu avec un travail humain authentique appelle à une discussion au sein des communautés scientifiques sur l'établissement de directives plus claires sur l'utilisation de l'IA dans la rédaction de recherches. À l'avenir, je m'engage à utiliser des outils comme Git et GitHub dès le départ pour toute mon écriture, assurant ainsi un enregistrement transparent de la progression de mon travail, dans le but de me protéger contre de telles accusations à l'avenir.


The illustration captures a whimsical and slightly devilish scene where ChatGPT 4, personified as a clever robot, rewrites and abridges an essay with a mischievous grin. Surrounded by books and papers in a cozy study, the scene combines creativity, wit, and a playful rebellion against traditional norms, highlighting the AI's role in authorship and translation, including a nod to its Canadian source material.

 ##  Le robot prend le rôle du journaliste.

News-Style Summary.  In a surprising turn of events, reported in Nature, a scientist studying ecological communities has been accused of using artificial intelligence, specifically ChatGPT, to write a research paper. The accusation, which focused on the "unusual" writing style, was made despite the scientist's commitment to data transparency and reproducibility. Defending their integrity, they highlighted their meticulous writing process and version-controlled documentation on GitHub. This incident has sparked a broader discussion on the impact of AI on scientific integrity and the need for clearer guidelines on AI's role in research writing.

##

/// GPT4.


(Lewis Black version).