Explore concepts like Self-Correct, Self-Refine, Self-Improve, Self-Contradict, Self-Play, and Self-Knowledge, alongside o1-like reasoning elevationš and hallucination alleviationš.
decoding self-improvement knowledge-distillation data-augmentation reasoning self-consistency preference-learning hallucination self-correction attention-head large-language-models chain-of-thought large-language-model internal-consistency self-feedback self-refine self-correct
-
Updated
Dec 7, 2024 - Jupyter Notebook