2 papers
cs.IR2024
Retro-li: Small-Scale Retrieval Augmented Generation Supporting Noisy Similarity Searches and Domain Shift Generalization
Gentiana Rashiti, Geethan Karunaratne, Mrinmaya Sachan +2
The retrieval augmented generation (RAG) system such as Retro has been shown to improve language modeling capabilities and reduce toxicity and hallucinations by retrieving from a d…
cs.LG2023
DSG: An End-to-End Document Structure Generator
Johannes Rausch, Gentiana Rashiti, Maxim Gusev +2
Information in industry, research, and the public sector is widely stored as rendered documents (e.g., PDF files, scans). Hence, to enable downstream tasks, systems are needed that…