Author

Rankyung Hong

h-index 3 View on Semantic Scholar

We have 1 of 8 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Evaluating LLM Knowledge Placement Techniques for Carbon-Efficiency

This work compares the trade-offs between retrieval-augmented generation, prefix caching, and fine-tuning in large language models to show that when the knowledge is stable and matches the questions asked, fine-tuning is the greenest, fastest, and most accurate, because it produces shorter answers.

Rankyung Hong · 0 citations