2 papers
cs.IR2025
Towards End-to-End Model-Agnostic Explanations for RAG Systems
Viju Sudhi, Sinchana Ramakanth Bhat, Max Rudat +2
Retrieval Augmented Generation (RAG) systems, despite their growing popularity for enhancing model response reliability, often struggle with trustworthiness and explainability. In…
cs.IR2025
Rethinking Chunk Size For Long-Document Retrieval: A Multi-Dataset Analysis
Sinchana Ramakanth Bhat, Max Rudat, Jannis Spiekermann +1
Chunking is a crucial preprocessing step in retrieval-augmented generation (RAG) systems, significantly impacting retrieval effectiveness across diverse datasets. In this study, we…