NumColBERT: Non-Intrusive Numeracy Injection for Late-Interaction Retrieval Models
@makiart13 et al. enhance ColBERT's handling of numerically conditioned queries via a numerical gating mechanism and contrastive loss.
📝 https://t.co/7rF8IWaMf9
👨🏽💻 https://t.co/ljazzLGCjh
🎉2026年7月にオーストラリア・メルボルンで開催される #SIGIR2026 に情報検索リサーチグループから2本の論文が採択されました! Two papers from the Information Retrieval Research Group have been accepted to #SIGIR2026, which will be held in Melbourne, Australia in July 2026! 👇
Recently, I was wondering how neural retrievers would perform when trained only based on LLM-revised corpora and queries.
Today, I came across this very insightful paper at @ACMSIGIR_AP by @dev_nakachi and @cyby that answers exactly that.
📝Paper: https://t.co/nX4oYHf5f6
🎉2025年12月に中国西安で開催されるSIGIR-AP 2025に筑波大情報検索グループから4本の論文が採択されました! Four papers from the IR Group at Tsukuba have been accepted to SIGIR-AP 2025, which will be held in Xi’an, China in December 2025!
👉 https://t.co/kMGPi9Qvx1