Ever wonder how test-time compute would do in retrieval? 🤔 introducing ✨rank1✨ rank1 is distilled from R1 & designed for reranking. rank1 is state-of-the-art at complex reranking tasks in reasoning, instruction-following, and general semantics (often 2x RankLlama 🤯) 🧵

We use this collection of tasks to propose multiple benchmarks for multilingual, code, European and Indic languages, and many more. We find that smaller multilingual models (~500M) outperform notably larger 7B models, likely due to a limited multilingual pre-training.

Check out our new encoder model, ModernBERT! 🤖 Super grateful to have been part of such an awesome team effort and very excited about the gains for retrieval/RAG! 🚀

Jeremy Howard @howard.fm · 2y ago

I'll get straight to the point. We trained 2 new models. Like BERT, but modern. ModernBERT. Not some hypey GenAI thing, but a proper workhorse model, for retrieval, classification, etc. Real practical stuff. It's much faster, more accurate, longer context, and more useful. 🧵

MASC is such a fun time! If your university is in the mid-Atlantic, please consider hosting!

@masc-conference.bsky.social · 2y ago

📢 Want to host MASC 2025? The 12th Mid-Atlantic Student Colloquium is a one day event bringing together students, faculty and researchers from universities and industry in the Mid-Atlantic. Please submit this very short form if you are interested in hosting! Deadline January 6th. #MASC2025

I'm looking for an intern to introduce Sparse Embedding models to Sentence Transformers! If you're passionate about open source, interested in helping practitioners use your tools, and enjoy embedders/retrievers/rerankers, then I'd love to hear from you! Links with details and to apply in 🧵

I noticed a lot of starter packs skewed towards faculty/industry, so I made one of just NLP & ML students: go.bsky.app/vju2ux Students do different research, go on the job market, and recruit other students. Ping me and I'll add you!

Creating a 🦋 starter pack for people working in IR/RAG: go.bsky.app/88ULgwY I can’t seem to find everyone though, help definitely appreciated to fill this out (DM or comment)!

Using LLMs for query or document expansion in retrieval (e.g. HyDE and Doc2Query) have scores going 📈 But do these approaches work for all IR models and for different types of distribution shifts? Turns out its actually more 📉 🚨 📝 (arxiv soon): orionweller.github.io/assets/pdf/L...