Settings

Theme

Baidu's Improving Retrieval Augmented Language Model with Self-Reasoning

arxiv.org

66 points by a-s-k-af 2 years ago · 5 comments

Reader

kaspermarstal 2 years ago

Can anyone explain what is gained by training a model? Why not use the foundational LLM for the relevance, evidence, and trajectory processes?

  • a-s-k-afOP 2 years ago

    I assume you are referring to fine tuning a model here?

    • Tostino 2 years ago

      You could also just continue pre-training of an existing foundation model. Would still be cheaper by not starting from zero.

      • a-s-k-afOP 2 years ago

        The amount of accuracy while doing fine tuning or distillation is usually better than pre-training an existing model, not to mention the graph against the cost.

Keyboard Shortcuts

j
Next item
k
Previous item
o / Enter
Open selected item
?
Show this help
Esc
Close modal / clear selection