ACL Findings2026
PatentMind: A Multi-Aspect Reasoning Graph for Patent Similarity Evaluation
Abstract
Patent similarity evaluation is essential for intellectual property analysis, yet existing methods struggle to capture the multifaceted structure of patent documents encompassing technical specifications, legal boundaries, and application contexts. We propose PatentMind, a framework that performs patent similarity assessment through a Multi-Aspect Reasoning Graph (MARG). PatentMind decomposes patent documents into three dimensions: technical features, application domains, and claim scopes, and computes dimension-specific similarity scores, which are then integrated via a context-aware dynamic weighting mechanism that emulates expert-level judgment. To facilitate evaluation, we introduce PatentSimBench, an expertannotated benchmark comprising 500 patent pairs. Experiments show that PatentMind achieves a Pearson correlation of r = 0.938 with expert annotations, substantially outperforming embedding-based, patent-specific, and prompt engineering baselines. Our framework offers interpretable, multi-dimensional assessment applicable to downstream tasks such as prior art search and infringement risk analysis.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
- Tree of Thoughts: Deliberate Problem Solving with Large Language Models cites Language Models are Few-Shot Learners
- Tree of Thoughts: Deliberate Problem Solving with Large Language Models cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
- Large Language Models are Zero-Shot Reasoners cites Language Models are Few-Shot Learners
- Large Language Models are Zero-Shot Reasoners cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
Builds on4
- Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah et al.NeurIPS 2020 · 64,255 citations
- Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsJason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma et al.NeurIPS 2022 · 22,562 citations
- Large Language Models are Zero-Shot ReasonersTakeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo et al.NeurIPS 2022 · 8,168 citations
- Tree of Thoughts: Deliberate Problem Solving with Large Language ModelsShunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran et al.NeurIPS 2023 · 5,068 citations
Related papers
- PatentScore: Multi-dimensional Evaluation of LLM-Generated Patent ClaimsYongmin Yoo, Qiongkai Xu, Longbing CaoEMNLP 2025 · 1 citation
- P-QuASAR: A Unified Probabilistic Framework for Holistic Patent Quality Assessment and RefinementXinyuan Song, Ziyi Ni, Fred Yang, Bo Zhang et al.ACL Findings 2026
- Enhancing the Patent Matching Capability of Large Language Models via the Memory GraphQiushi Xiong, Zhipeng Xu, Zhenghao Liu, Mengjia Wang et al.SIGIR 2025 · 4 citations
- Towards IP Intelligence: Benchmarking Large Language Models on Intellectual Property Knowledge and PracticeQiyao Wang, Guhong Chen, Hongbo Wang, Huaren Liu et al.ACL Findings 2026
- Inventive Problem Solving with LLMs: A Benchmark for TRIZ ReasoningZhu Wang, Brian UzziACL Findings 2026 · 1 citation
