Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
University of Glasgow
3
0
4
Only 20.9% of queries benefit from Pseudo-Relevance Feedback, highlighting a critical need for explainability in information retrieval systems.
By grounding adaptive retrieval in interpretable uncertainty signals, this framework transforms how LLMs handle knowledge gaps and ambiguities in real-time.
Achieving up to 99% reduction in trainable parameters without sacrificing recommendation performance could revolutionize how we approach multimodal recommendation systems.