Detection algorithms also fail to distinguish between answers from real people and large language models
OpenAI's ChatGPT outperforms the average university student in computer science, according to researchers, but interestingly, not in math.
The team led by Talal Rahwan and Yasir Zaki, both associate professors in computer science at New York University Abu Dhabi , found that ChatGPT outperformed students most markedly in a course called"Introduction to Public Policy," in which its average grade was 9.56 compared to an average of 4.39 for students.
Both students' and ChatGPT's answers were then compiled into a single document in random order, and graded by assessors who did not know which came from a person, and which from the LLM.
Belgique Dernières Nouvelles, Belgique Actualités
Similar News:Vous pouvez également lire des articles d'actualité similaires à celui-ci que nous avons collectés auprès d'autres sources d'information.
Be careful asking ChatGPT questions about cancer, Brigham study saysBe careful asking ChatGPT questions about cancer, Brigham study says
Lire la suite »
ChatGPT shows limited ability to recommend guidelines-based cancer treatmentsFor many patients, the internet serves as a powerful tool for self-education on medical topics. With ChatGPT now at patients' fingertips, researchers from Brigham and Women's Hospital, a founding member of the Mass General Brigham health care system, assessed how consistently the artificial intelligence chatbot provides recommendations for cancer treatment that align with National Comprehensive Cancer Network (NCCN) guidelines.
Lire la suite »
AI can achieve better grades than university students, report suggestsNew research found Sam Altman's ChatGPT matched or performed better than students when answering assessment questions. Model outperformed in psychology and others.
Lire la suite »
AI can achieve better grades than university students, report suggestsNew research found Sam Altman's ChatGPT matched or performed better than students when answering assessment questions. Model outperformed in psychology and others.
Lire la suite »
AI can achieve better grades than university students, report suggestsNew research found Sam Altman's ChatGPT matched or performed better than students when answering assessment questions. Model outperformed in psychology and others.
Lire la suite »
Scientists hope AI will speed up brain tumor diagnosisArtificial intelligence could raise hope of an early detection of brain tumors with the prospect of overcoming current limitations of diagnosis by conventional methods, new research suggests.
Lire la suite »