3 papers
cs.IR2026
Closing the Operational Gap in Semantic Caching
Aditeya Baral, Radoslav Ralev, Iliya Sotirov Zhechev +2
Semantic caching cuts LLM inference costs by serving a cached response to semantically similar queries. Standard practice evaluates these systems using PR-AUC, a metric that only m…
cs.IR2026
Training for Compositional Sensitivity Reduces Dense Retrieval Generalization
Radoslav Ralev, Aditeya Baral, Iliya Zhechev +2
Dense retrieval compresses texts into single embeddings ranked by cosine similarity. While efficient for recall, this interface is brittle for identity-level matching: minimal comp…
cs.CL2023
Multilingual Word Embeddings for Low-Resource Languages using Anchors and a Chain of Related Languages
Viktor Hangya, Silvia Severini, Radoslav Ralev +2
Very low-resource languages, having only a few million tokens worth of data, are not well-supported by multilingual NLP approaches due to poor quality cross-lingual word representa…