Re:How do domain-specific chatbots work? A retrieval augment...
by ingridpan on Friday August 25, 2023 @01:32PM
(#37264554)
RAG is great for pulling some additional knowledge, but if you combine it with fine-tuning (i.e., the LLM 'understands' the domain-specific terminology better) it becomes a lot more effective
[ Parent
| on HN ]
Re:How do domain-specific chatbots work? A retrieval augment...
by monkeydust on Friday August 25, 2023 @01:55PM
(#37264865)
Looking exactly into this, any research on this topic?
Re:How do domain-specific chatbots work? A retrieval augment...
by ingridpan on Friday August 25, 2023 @02:24PM
(#37265325)
Research:
https://arxiv.org/abs/2005.11401
An implementation on Hugging Face: https://huggingface.co/docs/transformers/model_doc/rag
Re:How do domain-specific chatbots work? A retrieval augment...
by monkeydust on Friday August 25, 2023 @02:55PM
(#37265734)
Txs but I meant fine tuning and RAG combined