Skip to content
conftrace_
2025 COLING COLING 2025

Shared Task RIRAG-2025: Regulatory Information Retrieval and Answer Generation

Abstract

AbstractThis paper provides an overview of the Shared Task RIRAG-2025, which focused on advancing the field of Regulatory Information Retrieval and Answer Generation (RIRAG). The task was designed to evaluate methods for answering regulatory questions using the ObliQA dataset. This paper summarizes the shared task, participants’ methods, and the results achieved by various teams.

🌉 Interdisciplinary Bridge - Computer Science and Natural Language Processing

Authors

Tuba Gokhan, Kexin Wang, Iryna Gurevych, Ted Briscoe

Topics

Natural Language Processing > Applications > Information Retrieval Natural Language Processing > Applications > Question Answering Computer Science > Applications > Information Retrieval

Keywords

question answering information retrieval shared task regulatory text regulatory information retrieval answer generation large language model
Download PDF

More from COLING 2025

All COLING 2025 papers →
Emergence of symbolic abstraction heads for in-context learning in large language models
Linking language model predictions to human behaviour on scalar implicatures
Generative FrameNet: Scalable and Adaptive Frames for Interpretable Knowledge Storage and Retrieval for LLMs Powered by LLMs
Challenges in Technical Regulatory Text Variation Detection
Bilingual BSARD: Extending Statutory Article Retrieval to Dutch
Unifying Large Language Models and Knowledge Graphs for efficient Regulatory Information Retrieval and Answer Generation