Mastering Retrieval for LLMs - BM25, Fine-tuned Embeddings, and Re-Rankers

Mastering Retrieval for LLMs - BM25, Fine-tuned Embeddings, and Re-Rankers

Trelis Research via YouTube Direct link

Re-rankers

15 of 19

15 of 19

Re-rankers

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Mastering Retrieval for LLMs - BM25, Fine-tuned Embeddings, and Re-Rankers

Automatically move to the next video in the Classroom when playback concludes

  1. 1 Mastering Retrieval RAG for LLMs
  2. 2 Video Overview
  3. 3 Baseline Performance with No Retrieval
  4. 4 Document Chunking - Naive vs Sentence based
  5. 5 BM25
  6. 6 Semantic / Vector / Embeddings Search
  7. 7 Cosine vs Dot Product Similarity
  8. 8 Generating Chunks and Embeddings
  9. 9 Running BM25 and Similarity Retrieval
  10. 10 Performance with BM25 vs Similarity
  11. 11 Fine-tuning embeddings / encoders
  12. 12 Preparing fine-tuning datasets
  13. 13 Embeddings Training Continued
  14. 14 Performance after Fine-tuning
  15. 15 Re-rankers
  16. 16 : Cross-encoders
  17. 17 LLM re-rankers
  18. 18 Re-ranking performance
  19. 19 Final Tips

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.