Knowledge Tree

Relations (1)

related 2.32 — strongly supporting 4 facts

GPT-4 and gpt-4o-mini are related as members of the OpenAI GPT model family, frequently compared in performance benchmarks [1] and utilized together in research frameworks like KG-IRAG [2] and RAGAS++ [3].

Facts (4)

Sources

Medical Hallucination in Foundation Models and Their Impact on ... medrxiv.org medRxiv 2 facts

measurementThe AI model o1 achieves a hallucination resistance baseline of 64.0%, while earlier-generation models gpt-4o and gpt-4o-mini achieve baselines of 54.4% and 48.3% respectively.

measurementOpenAI released GPT-4o in May 2024 and GPT-4o mini in July 2024.

Benchmarking Hallucination Detection Methods in RAG - Cleanlab cleanlab.ai Cleanlab 1 fact

procedureRAGAS++ is a refined variant of the RAGAS technique developed by Cleanlab that uses the gpt-4o-mini LLM for generation and as a critic, replacing the default gpt-3.5-turbo-16k and gpt-4 models.

Large Language Models Meet Knowledge Graphs for Question ... arxiv.org arXiv 1 fact

referenceKG-IRAG, as described by Yang et al. (2025), utilizes incremental retrieval and iterative reasoning with Llama-3-8B-Instruct, GPT-3.5-Turbo, GPT-4o-mini, and GPT-4o models on self-constructed knowledge graphs for temporal QA tasks.