Fig 1 - uploaded by Dimitri Ognibene
Content may be subject to copyright.
Source publication
Artificial intelligence's progress holds great promise in assisting society in addressing pressing societal issues. In particular Large Language Models (LLM) and the derived chatbots, like ChatGPT, have highly improved the natural language processing capabilities of AI systems allowing them to process an unprecedented amount of unstructured data. T...
Contexts in source publication
Context 1
... aim of the workshop was to introduce students to the topic of AI and encourage them to explore and question the capabilities and limitations of ChatGPT. The study procedure, depicted in Figure 1, was designed to facilitate learning through active exploration. In particular, the educational learning plan saw two phases, the first one introduced students to AI and allowed them to freely explore the capabilities and limitations of ChatGPT and the second phase introduced students to techniques to enhance ChatGPTs capabilities. ...
Context 2
... aim of the workshop was to introduce students to the topic of AI and encourage them to explore and question the capabilities and limitations of ChatGPT. The study procedure, depicted in Figure 1, was designed to facilitate learning through active exploration. In particular, the educational learning plan saw two phases, the first one introduced students to AI and allowed them to freely explore the capabilities and limitations of ChatGPT and the second phase introduced students to techniques to enhance ChatGPTs capabilities. ...
Similar publications
Language model (LM) post-training (or alignment) involves maximizing a reward function that is derived from preference annotations. Direct Preference Optimization (DPO) is a popular offline alignment method that trains a policy directly on preference data without the need to train a reward model or apply reinforcement learning. However, typical pre...
When answering questions, LLMs can convey not only an answer, but a level of confidence about the answer being correct. This includes explicit confidence markers (e.g. giving a numeric score) as well as implicit markers, like an authoritative tone or elaborating with additional knowledge. For LLMs to be trustworthy knowledge sources, the confidence...
Artificial intelligence’s (AI) progress holds great promise in tackling pressing societal concerns such as health and climate. Large Language Models (LLM) and the derived chatbots, like ChatGPT, have highly improved the natural language processing capabilities of AI systems allowing them to process an unprecedented amount of unstructured data. Howe...
Citations
A 21. században a technológiai fejlődésnek köszönhetően gyorsan bővül azon képességek köre, amelyek meghatározzák a mindennapi életünket, amelyekkel munkavállalóként rendelkeznünk kell, amelyeket a tanulástanítás folyamata során a pedagógusoknak, az oktatóknak fejlesztenie szükséges. A generatív mesterséges
intelligencia megjelenésével előtérbe került, a kritikus gondolkodás magasabb szintre emelése mellett, a promptolás képessége is. A minőségi tartalmak létrehozásához elengedhetetlen, hogy ismerjük a promptalkotás lépéseit, befolyásoló tényezőit, nyelvi jellemzőit. Írásunkban azt járjuk körbe, hogy milyen ismeretekre van szükség e képesség kialakításához és fejlesztéséhez.
