ChatGPT, Computational Semantics and Large Language Models

Enhancing LLM Reliability: Detecting Confabulations with Semantic Entropy

Marktechpost

JUNE 22, 2024

LLMs like ChatGPT and Gemini demonstrate impressive reasoning and answering capabilities but often produce “hallucinations,” meaning they generate false or unsupported information. Semantic entropy is a method to detect confabulations in LLMs by measuring their uncertainty over the meaning of generated outputs.

LLM

LLM Computational Semantics ChatGPT ML

Small but Mighty: The Enduring Relevance of Small Language Models in the Age of LLMs

Marktechpost

SEPTEMBER 15, 2024

Large Language Models (LLMs) have revolutionized natural language processing in recent years. The pre-train and fine-tune paradigm, exemplified by models like ELMo and BERT, has evolved into prompt-based reasoning used by the GPT family.

BERT

BERT LLM Large Language Models Categorization

Artificial Intelligence Zone

Enhancing LLM Reliability: Detecting Confabulations with Semantic Entropy

Small but Mighty: The Enduring Relevance of Small Language Models in the Age of LLMs

Webinars

Stay Connected