2 papers
cs.IR2026
ColBERT-Att: Late-Interaction Meets Attention for Enhanced Retrieval
Raj Nath Patel, Sourav Dutta
Vector embeddings from pre-trained language models form a core component in Neural Information Retrieval systems across a multitude of knowledge extraction tasks. The paradigm of l…
cs.CL2025
SafePassage: High-Fidelity Information Extraction with Black Box LLMs
Joe Barrow, Raj Patel, Misha Kharkovski +2
Black box large language models (LLMs) make information extraction (IE) easy to configure, but hard to trust. Unlike traditional information extraction pipelines, the information "…