[HN Gopher] Improving Text Embeddings with Large Language Models
___________________________________________________________________
Improving Text Embeddings with Large Language Models
Author : cmcollier
Score : 32 points
Date : 2024-01-02 18:59 UTC (4 hours ago)
(HTM) web link (arxiv.org)
(TXT) w3m dump (arxiv.org)
| binarymax wrote:
| Interesting, but this aspect makes me double-take: "We
| demonstrate that Mistral-7B, when fine-tuned solely on synthetic
| data, attains competitive performance on the BEIR [ 40 ] and MTEB
| [27] benchmarks".
|
| E5/BGE large are an order of magnitude smaller than Mistral-7B.
| So is this just "bigger model wins" in disguise?
|
| I need to read the whole paper carefully, but this jumped out at
| me.
| huac wrote:
| agree, this is a nice example of generating synthetic data, and
| I believe that the synthetic data is helpful for generating
| useful embeddings for RAG, but not including an ablation with
| fine-tuned E5 or another commonly used embedding model (to
| control for the 'bigger model wins' effect) is a glaring
| omission. this paper shares many authors with the E5 paper, why
| did they not compare on a fair basis?
___________________________________________________________________
(page generated 2024-01-02 23:01 UTC)