LLM-KG skills evolution time capsule 2023 for Claude & ChatGPT - Results and log of LLM-KG-Bench runs
Johannes Frey, Lars‐Peter Meyer, Felix Brei, Sabine Gründer-Fahrer, Michael Martin · Zenodo (CERN European Organization for Nuclear Research) · 2024
The json files contain parameters, conversations and evaluations of different Claude and ChatGPT runs with LLM-KG-Bench in 2023.Re-evaluation is possible with LLM-KG-Bench using the --reeval parameter, thus allowing for repeated or modified evaluation (e.g. different metrics, parser libraries, scores, etc). For LLM-KG-Bench framework see https://github.com/AKSW/LLM-KG-Bench or DOI:10.5281/zenodo.8366061