Learning Dynamics of LLM Finetuning

Decomposes prediction changes during language-model fine-tuning. The framework connects interactions between responses with repetition, hallucination, and decreasing preferred-response probability during prolonged DPO training.

Decomposes prediction changes during language-model fine-tuning. The framework connects interactions between responses with repetition, hallucination, and decreasing preferred-response probability during prolonged DPO training.

When reading the original paper, identify its problem, inputs, outputs, and methodological assumptions.

Decomposes prediction changes during language-model fine-tuning. The framework connects interactions between responses with repetition, hallucination, and decreasing preferred-response probability during prolonged DPO training.

Check the baselines, datasets, evaluation protocol, and ablations in the original paper. This directory overview does not provide an independent evaluation or experimental results table.