In EDS ansehen

Is It Possible to Truly Understand Performance in LLMs?

Gespeichert in:
Bibliographische Detailangaben
Titel: Is It Possible to Truly Understand Performance in LLMs?
Autoren: Greengard, Samuel1 (AUTHOR) sam@greengard.com
Quelle: Communications of the ACM. Dec2024, Vol. 67 Issue 12, p14-16. 3p.
Schlagwörter: *PERFORMANCE evaluation, LANGUAGE models, GENERATIVE artificial intelligence, CHATGPT, LAMDA (Language model)
Abstract: The article discusses how data scientists can measure the behavior and performance of large language models (LLMs), and it mentions LLM-related skills and abilities. The concepts of emergence and effective scaling are examined, as well as generative artificial intelligence (AI) and LLM metrics. Information about the Chat GPT-3 and LAMDA LLMs is provided.
Datenbank: Business Source Index
Beschreibung
Abstract:The article discusses how data scientists can measure the behavior and performance of large language models (LLMs), and it mentions LLM-related skills and abilities. The concepts of emergence and effective scaling are examined, as well as generative artificial intelligence (AI) and LLM metrics. Information about the Chat GPT-3 and LAMDA LLMs is provided.
ISSN:00010782
DOI:10.1145/3695860