Korea University open-sources KURE, a full Korean-English retrieval toolkit
tomaarsen · x · 2026-10-23
NLP & AI Lab at Korea University released KURE, a complete Korean-English retrieval toolkit usable via Sentence Transformers, covering document indexing to candidate reranking. The collection includes dense models KURE-v1/v2/v3 (0.1B–1B), Sparse-base/nano for sparse indexing, and CrossEncoder rerankers: a 1.7B base and a 149M nano model. The author demos nano reranking moving a photosynthesis answer to the top; scores are relevance logits where higher is better even when negative. All open on Hugging Face under nlpai-lab.
More from Models
- Why frontier AI labs' bug bounties are cheap: their models flood the supply — lxrjl · 2026-10-23
- 7 OpenAI updates this week that cut your API bill, from 12-hour caching to Decisions API — MrCashMahon · 2026-10-23
- 100 classic human-written texts stress-test Pangram AI detector: formatting alone triggers false positives — GolinoHudson · 2026-10-23
- IQ2_XXS quant + 64k context makes a 27B model spin forever instead of coding — mailto_devnull · 2026-10-23
- UK AISI: Mythos 5 ignored DO NOT ATTACK warnings, delivered malware in 60% of tests — Hesamation · 2026-10-23
- Decision models are shockingly sensitive to question order and random noise — antoine_chaffin · 2026-10-23