GPT 3.5 ↔ Large Language Models

Relations (1)

related 2.00 — strongly supporting 3 facts

GPT-3.5 is a specific instance of Large Language Models, as evidenced by its inclusion in comparative studies of LLM behavior [1], its role as a model subject to adversarial attacks alongside other LLMs [2], and its application in knowledge graph construction tasks alongside other state-of-the-art large language models [3].

Facts (3)

Sources

Building Trustworthy NeuroSymbolic AI Systems - arXiv arxiv.org arXiv 1 fact

referenceZiems et al. (2022) conducted experiments on seven different Large Language Models using a moral integrity dataset comprising 20,000 samples and instructions to investigate whether GPT-3.5's behavior regarding moral questions is unique.

Track: Poster Session 3 - aistats 2026 virtual.aistats.org Samuel Tesfazgi, Leonhard Sprandl, Sandra Hirche · AISTATS 1 fact

claimAdversarial attacks on Large Language Models (LLMs) for time series forecasting lead to more severe performance degradation than random noise across models including LLMTime with GPT-3.5, GPT-4, LLaMa, Mistral, TimeGPT, and TimeLLM.

Unknown source 1 fact

claimThe research paper 'Towards the Automation of Knowledge Graph Construction Using ...' explores the semi-automatic and automatic construction of knowledge graphs using state-of-the-art large language models including Mixtral 8x22B Instruct v0.1, GPT-4o, and GPT-3.5.