Retrieval-Augmented Classification of Environmental Mitigations in Hydropower Licensing Documents
2026-08-24 • Information Retrieval
Information RetrievalArtificial Intelligence
AI summaryⓘ
The authors worked on a project to automatically identify different environmental rules in government hydropower documents. They found it hard because many categories had little or no examples for training. Their usual BERT model worked well on common categories but failed on unseen ones. To fix this, they built a system that uses a method called Retrieval-Augmented Generation (RAG) to understand new categories without prior examples. Combining BERT with RAG gave the best results on the full set of documents.
Hydropower licensingEnvironmental mitigationMulti-label classificationBERTRetrieval-Augmented Generation (RAG)Zero-shot learningF1 scoreNatural language processingLabel scarcityTaxonomy
Authors
Hong-Jun Yoon, Tom Ruggles, Joanna Lee, Debjani Singh
Abstract
Identifying and classifying environmental mitigation obligations in Federal Energy Regulatory Commission hydropower licensing documents is a labor-intensive task requiring deep domain expertise. We formulate this as a multi-label classification problem over a structured 135-category taxonomy and address the central challenge of severe label scarcity: 40 of 135 categories have no training examples, and 26 have fewer than five. A supervised Bidirectional Encoder Representations from Transformers (BERT)-based pipeline, while effective on well-represented categories, achieves F1 of zero on unseen classes regardless of augmentation strategy. We introduce a Retrieval-Augmented Generation (RAG) pipeline that conditions classification on retrieved category definitions, enabling zero-shot generalization across the full label space. We further propose a hybrid system that combines BERT detection with RAG classification, exploiting the high recall of fine-tuned detection and the zero-shot coverage of retrieval-augmented reasoning. Evaluated on the full set of 2017 license documents (5,860 paragraphs, 135 categories), the hybrid achieves a Micro F1 of 0.524, outperforming the BERT-only pipeline (0.477) and the RAG-only pipeline (0.416) across all training-support buckets.