Adaptive Multi-Stage Patent Claim Generation with Unified Quality Assessment
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908763724709888 |
|---|---|
| author | Liang, Chen-Wei Guo, Bin Wei, Zhen-Yuan Wang, Mu-Jiang-Shan |
| author_facet | Liang, Chen-Wei Guo, Bin Wei, Zhen-Yuan Wang, Mu-Jiang-Shan |
| contents | Current patent claim generation systems face three fundamental limitations: poor cross-jurisdictional generalization, inadequate semantic relationship modeling between claims and prior art, and unreliable quality assessment. We introduce a novel three-stage framework that addresses these challenges through relationship-aware similarity analysis, domain-adaptive claim generation, and unified quality assessment. Our approach employs multi-head attention with eight specialized heads for explicit relationship modeling, integrates curriculum learning with dynamic LoRA adapter selection across five patent domains, and implements cross-attention mechanisms between evaluation aspects for comprehensive quality assessment. Extensive experiments on USPTO HUPD dataset, EPO patent collections, and Patent-CE benchmark demonstrate substantial improvements: 7.6-point ROUGE-L gain over GPT-4o, 8.3\% BERTScore enhancement over Llama-3.1-8B, and 0.847 correlation with human experts compared to 0.623 for separate evaluation models. Our method maintains 89.4\% cross-jurisdictional performance retention versus 76.2\% for baselines, establishing a comprehensive solution for automated patent prosecution workflows. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_09120 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Adaptive Multi-Stage Patent Claim Generation with Unified Quality Assessment Liang, Chen-Wei Guo, Bin Wei, Zhen-Yuan Wang, Mu-Jiang-Shan Computation and Language Artificial Intelligence 68T50, 68T05 I.2.7; H.3.3; I.2.11 Current patent claim generation systems face three fundamental limitations: poor cross-jurisdictional generalization, inadequate semantic relationship modeling between claims and prior art, and unreliable quality assessment. We introduce a novel three-stage framework that addresses these challenges through relationship-aware similarity analysis, domain-adaptive claim generation, and unified quality assessment. Our approach employs multi-head attention with eight specialized heads for explicit relationship modeling, integrates curriculum learning with dynamic LoRA adapter selection across five patent domains, and implements cross-attention mechanisms between evaluation aspects for comprehensive quality assessment. Extensive experiments on USPTO HUPD dataset, EPO patent collections, and Patent-CE benchmark demonstrate substantial improvements: 7.6-point ROUGE-L gain over GPT-4o, 8.3\% BERTScore enhancement over Llama-3.1-8B, and 0.847 correlation with human experts compared to 0.623 for separate evaluation models. Our method maintains 89.4\% cross-jurisdictional performance retention versus 76.2\% for baselines, establishing a comprehensive solution for automated patent prosecution workflows. |
| title | Adaptive Multi-Stage Patent Claim Generation with Unified Quality Assessment |
| topic | Computation and Language Artificial Intelligence 68T50, 68T05 I.2.7; H.3.3; I.2.11 |
| url | https://arxiv.org/abs/2601.09120 |