Towards General Text Embeddings with Multi-stage Contrastive Learning · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2308.03281/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTTowards General Text Embeddings with Multi-stage Contrastive Learning — mentioned by ntonozzihttps://news.ycombinator.com/item?id=41780316urn:hackerpapers:mention:2308.03281:41780316Tue, 08 Oct 2024 18:29:23 GMT<p>One important factor this article neglects to mention is that modern text embedding models are trained to maximize distance of dissimilar texts under a specific metric. This means that the embedding vector is not just latent weights plucked from the last layer of a model, but instead specifically trained to be used with a particular distance function, which is the cosine distance for all the models I&#x27;m familiar with. You can learn more about how modern embedding models are trained from papers like Towards General Text Embeddings with Multi-stage Contrastive Learning…</p><p><a href="https://hackerpaper.kaipfister.de/p/2308.03281/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CL