colbertv2-f4443d65·2 events·first seen Aliases: ColBERTv2, ColBERT
Researchers release DenseOn and LateOn, two 149M-parameter retrieval models trained on a fully open, reproducible pipeline using 665M curated English contrastive pairs and 1.88M supervised fine-tuning pairs. Both models achieve new state-of-the-art results for their size class on BEIR (56.20 and 57.22 nDCG@10 respectively). Multilingual variants (mDenseOn, mLateOn) are trained via translate-train on 2.8B pairs, revealing that late-interaction (ColBERT-style) token-level matching generalizes better to unseen languages than dense single-vector models. All models, datasets, and training code are publicly released.
A new arXiv preprint introduces HKVM-RAG, an evidence-organization layer for multi-hop RAG that uses weighted hyperedges as retrieval keys while retaining passage text as answer values. Under a fixed-substrate protocol controlling for tuple cache, reader, and evaluation budget, the hypergraph key-value approach improves over KG-PPR by +3.4 F1 on 2WikiMultiHopQA and +3.6 F1 on MuSiQue. A dense-aware controller combining frozen ColBERTv2 with HKVM features reaches 88.8, 65.1, and 85.8 F1 on three benchmarks, outperforming ColBERTv2 alone by 5–11 F1 points. The work positions hypergraph organization as a reusable evidence-control mechanism rather than a dense-retrieval replacement.