Large Language Models (LLMs) like ChatGPT or Bard have revolutionized information retrieval and captivated the audience with their ability to generate custom responses in record time, regardless of the topic. In this article, we assess the capabilities of various LLMs in producing reliable, comprehensive, and sufficiently relevant responses about historical facts in French. To achieve this, we constructed a testbed comprising numerous history-related questions of varying types, themes, and levels of difficulty. Our evaluation of responses from ten selected LLMs reveals numerous shortcomings in both substance and form. Beyond an overall insufficient accuracy rate, we highlight uneven treatment of the French language, as well as issues related to verbosity and inconsistency in the responses provided by LLMs.

Large language models (LLMs) have been leveraged for several years now, obtaining state-of-the-art performance in recognizing entities from modern documents. For the last few months, the conversational agent ChatGPT has "prompted" a lot of interest in the scientific community and public due to its capacity of generating plausible-sounding answers. In this paper, we explore this ability by probing it in the named entity recognition and classification (NERC) task in primary sources (e.g., historical newspapers and classical commentaries) in a zero-shot manner and by comparing it with state-of-the-art LM-based systems. Our findings indicate several shortcomings in identifying entities in historical text that range from the consistency of entity annotation guidelines, entity complexity, and code-switching, to the specificity of prompting. Moreover, as expected, the inaccessibility of historical archives to the public (and thus on the Internet) also impacts its performance.

According to research from Carnegie Mellon University kids solve math problems by going through four distinct stages: encoding (reading and understanding the problem); planning (working out how to tackle it); solving (crunching the numbers) and responding (typing in the correct answer). This follows the general path that is set out in school, but is not something missing? "We're not teaching them how to learn." Reflection and putting subjects in perspectives and in a general framework are all too often given too little space in school education. While at the same time this is the basic trigger for the ongoing extraordinary development of artificial intelligence.

Schools today look almost nothing like they did 50 years ago. According to Jonathan Rochelle, head of product management for Google Apps for Education, the next 50 years might see even crazier advances. By 2066, Rochelle says, schools are poised to become highly collaborative spaces, thanks to the advent of virtual and augmented reality. Instead of needing to meet in the same physical space, kids could work on long-term projects remotely and interact through online platforms. Rochelle has a unique perspective on the value of teamwork: In 2006, he co-founded the Google Docs suite.