Puerto, Haritz; Chubakov, Tilek; Zhu, Xiaodan; Tayyar Madabushi, Harish; Gurevych, Iryna. LLaMA-2 13B-Chat Model checkpoints for Fine-Tuning with Divergent Chains of Thought Boosts Reasoning Through Self-Correction in Language Models. (2024-06). CC BY-SA 3.0. LLM, large language model, NLP, chain of thought, cot, 409-05 Interaktive und intelligente Systeme, Bild- und Sprachverarbeitung, Computergraphik und Visualisierung, 004. Technical University of Darmstadt. https://tudatalib.ulb.tu-darmstadt.de/handle/tudatalib/4272