You are viewing a single comment's thread from:

RE: LeoThread 2025-10-18 17-00

in LeoFinancelast month

Part 7/13:

  • Better alternatives exist: Prompt engineering, retrieval-augmented generation (RAG), and traditional algorithms with embeddings can often provide sufficient results with less overhead.

For instance, in complex procedural questions that demand aggregating information from multiple document sections, I the speaker notes that even large fine-tuned models sometimes struggle, producing accuracy no better than 62-75%. This demonstrates that simpler, more transparent approaches may be preferable initially.

Essential Steps Before Fine-Tuning

The speaker advocates a careful sequence:

  1. Start with prompt engineering: Design prompts and benchmarks to evaluate initial performance.