Structured Reasoning in Language Models

Latest papers

65 papers19 papers in the last four weeks, up 217% on the four weeks before. 0.1% of all new papers.

Reasoning for Hierarchical Text Classification: The Case of Patents
Oct 8, 2025Lekang Jiang, Wenjun Sun, Stephan GoetzHierarchical Classification Text Classification
University of Cambridge · National Science Library, Chinese Academy of Sciences · Department of Information Resources Management, School of Economics and Management, University of Chinese Academy of Sciences
The Answer Lies Within: Self-Derived Rewards Enable Explainable Relation Extraction
Oct 7, 2025Xinyu Guo, Zhengliang Shi, Minglai Yang +2Relation Extraction Structured Reasoning in Language Models
University of Arizona, Tucson, AZ, United States · Shandong University, Qingdao, China.
Attention-Aligned Reasoning for Large Language Models
Oct 3, 2025Hongxiang Zhang, Yuan Tian, Tianyi ZhangLLM Reasoning Structured Reasoning in Language Models
Purdue University
Explore-Execute Chain: Towards an Efficient Structured Reasoning Paradigm
Sep 28, 2025Kaisen Yang, Tinghe Zhang, Rushi Shah +4LLM Reasoning Structured Reasoning
1Qizhi Institute · 2Dept. of Computer Science, Tsinghua University · College of AI, Tsinghua University +4
Beyond Empathy: Integrating Diagnostic and Therapeutic Reasoning with Large Language Models for Mental Health Counseling
May 21, 2025He Hu, Juzheng Si, Qianning Wang +5Mental Health Counseling Structured Reasoning in Language Models
College of Computer Science and Software Engineering, Shenzhen University · Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ) · Shandong University +2

Oct 8, 2025J/K move · Enter open · S save

Reasoning for Hierarchical Text Classification: The Case of Patents

Lekang Jiang, Wenjun Sun, Stephan Goetz

University of Cambridge · National Science Library, Chinese Academy of Sciences · Department of Information Resources Management, School of Economics and Management, University of Chinese Academy of Sciences

Hierarchical Classification Text Classification Explainable Text Classification Structured Reasoning in Language Models

Open paper AskPDF arXiv

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 chain-of-thought (CoT) reasoning format and a reinforcement learning (RL) stage to enhance multi-step 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 fine-tuning. (4) Applicability: Beyond patents, we further demonstrate that RHC achieves state-of-the-art performance on other widely used HTC benchmarks, which highlights its broad applicability.

Latest papers

Reasoning for Hierarchical Text Classification: The Case of Patents

The Answer Lies Within: Self-Derived Rewards Enable Explainable Relation Extraction

Attention-Aligned Reasoning for Large Language Models

Explore-Execute Chain: Towards an Efficient Structured Reasoning Paradigm

Beyond Empathy: Integrating Diagnostic and Therapeutic Reasoning with Large Language Models for Mental Health Counseling