RAG Pipeline Strategies for Ukrainian Multi-Domain Document Understanding Task

Balancing Reasoning and Hardware Constraints in RAG Pipelines for Ukrainian Multi-Domain Document Understanding

This paper describes the system submitted to the UNLP 2026 Shared Task on Multi-Domain Document Understanding. The challenge required extracting precise answers, document IDs, and page numbers from a diverse corpus of Ukrainian PDF documents within a strict 9-hour offline Kaggle execution limit. During evaluation on th...

Evaluating RAG approaches for Question Answering

DocHop: Benchmarking Out-of-domain Multi-hop Reasoning in Information-Dense Documents

This work introduces DocHop, a benchmark for integrated chart--context reasoning in document-style images and constructs DocHop via a stochastic logic-first generation pipeline with controllable reasoning depth and visual density, to enable systematic evaluation.

Hybrid Retrieval for Indic Language Question Answering using an Improved RAG Pipeline

Although Large Language Models (LLMs) have progressed significantly, Retrieval-Augmented Generation (RAG) still falls short for under-resourced Indic languages. Existing embedding systems, built primarily for English, face issues with script mismatches and limited word coverage, leading to near-complete retrieval failu...

ICDAR2026 Competition on Multimodal Reasoning over Documents in Multiple Domains

The results show that the strongest systems move beyond single-pass prompting and instead rely on structured evidence extraction, retrieval, verification, and orchestration across multiple components.

BengaliMCQ: Automatic Generation and Answer Prediction of Academic Multiple-Choice Questions in a Low-Resource Language

A structure-aware RAG framework is proposed that models Bengali textbooks as hierarchical graphs and uses a contrastively trained graph neural network to retrieve a small set of relevant passages, enabling topic-specific multiple-choice question (MCQ) generation and in-domain answer prediction.