arXiv AI By Meenu Ravi, Shailik Sarkar, Lulwah AlKulaib, Yordanos Tessema, Chang-Tien Lu

GeoRisk-RAG: A Hierarchy-Aware Risk Framework for Improving RAG Reliability through Selective Answering

Read the original on arXiv AI →

GeoRisk-RAG is a hierarchy‑aware framework that improves the reliability of Retrieval‑Augmented Generation (RAG) by incorporating geographic validity. It estimates geographic applicability using a Directed Acyclic Graph (DAG)‑based distance during context retrieval, enabling selective answering. Experiments on a wildfire‑related QA dataset show that GeoRisk‑RAG reduces false confidence rates from ~0.090 to 0.009 and aligns better with human preferences.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Computation and Language
2d ago

MAPLE: Metadata Conditioned LLM Pretraining for Locale-Aware Question Answering

The paper introduces MAPLE, a family of decoder‑only language models pretrained with document‑level geographic metadata such as source URL, country, and continent. MAPLE is evaluated on a new benchmark, LocalNewsQA, which tests whether models can switch answers when the locale changes. Experiments show that, with inference‑time metadata fixed, MAPLE outperforms metadata‑free controls in both answer switching and accuracy on locale‑dependent questions, and these gains grow with model size.

By Anjishnu Mukherjee, Ziwei Zhu, Antonios Anastasopoulos
Hugging Face Trending Papers
Jun 27

AB-RAG: Adaptive Budgeted Retrieval-Augmented Generation for Reliable Question Answering

Retrieval-Augmented Generation (RAG) has become the standard way to ground large language models in external knowledge, yet most systems retrieve a fixed number of passages for every question regardless of its difficulty. This wastes computation on easy questions, starves hard ones, and gives no signal for when a generated answer can be trusted.