Reasoning for Hierarchical Text Classification: The Case of Patents

Hierarchical text classification (HTC) assigns documents to multiple levels of a pre-defined taxonomy.Automated patent subject classification represents one of the hardest HTC scenarios because of professional difficulties and extensive labels.Prior approaches only output a flat label set, which offers little insight into the reason behind predictions.Therefore, we propose Reasoning for Hierarchical Classification (RHC), a novel framework that reformulates HTC as a step-by-step reasoning task to sequentially deduce hierarchical labels.RHC trains large language models (LLMs) in two stages: a cold-start stage that aligns outputs with chainof-thought (CoT) reasoning format and a reinforcement learning (RL) stage to enhance multistep reasoning ability.RHC demonstrates four advantages in our experiments.(1) Effectiveness: RHC surpasses previous baselines and outperforms the supervised fine-tuning counterparts by approximately 3% in accuracy and macro F1. (2) Explainability: RHC produces natural-language justifications before prediction to facilitate human inspection.(3) Scalability: RHC scales favorably with model size with larger gains compared to standard finetuning.(4) Applicability: Beyond patents, we further demonstrate that RHC achieves stateof-the-art performance on other widely used HTC benchmarks, which highlights its broad applicability. 1