# Adaptive Multi-Stage Patent Claim Generation with Unified Quality Assessment

arXiv: https://arxiv.org/abs/2601.09120 · HTML: https://mlsanity.com/paper/2601.09120/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 58 references that are in the map.
- First posted on arXiv 14 Jan 2026.

## Builds on (most cited first, 29 of 29)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [Lumina-DiMOO: An Omni Diffusion Large Language Model for Multi-Modal Generation and Understanding](https://mlsanity.com/paper/2510.06308/) (2025)
- [VMT-Adapter: Parameter-Efficient Transfer Learning for Multi-Task Dense Scene Understanding](https://mlsanity.com/paper/2312.08733/) (2023)
- [EvoFlow: Evolving Diverse Agentic Workflows On The Fly](https://mlsanity.com/paper/2502.07373/) (2025)
- [ReAgent-V: A Reward-Driven Multi-Agent Framework for Video Understanding](https://mlsanity.com/paper/2506.01300/) (2025)
- [Lumina-mGPT 2.0: Stand-Alone AutoRegressive Image Modeling](https://mlsanity.com/paper/2507.17801/) (2025)
- [The Harvard USPTO Patent Dataset: A Large-Scale, Well-Structured, and Multi-Purpose Corpus of Patent Applications](https://mlsanity.com/paper/2207.04043/) (2022)
- [WcDT: World-centric Diffusion Transformer for Traffic Scene Generation](https://mlsanity.com/paper/2404.02082/) (2024)
- [Surveying the MLLM Landscape: A Meta-Review of Current Surveys](https://mlsanity.com/paper/2409.18991/) (2024)
- [Reasoning in Computer Vision: Taxonomy, Models, Tasks, and Methodologies](https://mlsanity.com/paper/2508.10523/) (2025)
- [MVI-Bench: A Comprehensive Benchmark for Evaluating Robustness to Misleading Visual Inputs in LVLMs](https://mlsanity.com/paper/2511.14159/) (2025)
- [PaECTER: Patent-level Representation Learning using Citation-informed Transformers](https://mlsanity.com/paper/2402.19411/) (2024)
- [ForgetMe: Evaluating Selective Forgetting in Generative Models](https://mlsanity.com/paper/2504.12574/) (2025)
- [Twin Co-Adaptive Dialogue for Progressive Image Generation](https://mlsanity.com/paper/2504.14868/) (2025)
- [Is GPT-OSS Good? A Comprehensive Evaluation of OpenAI's Latest Open Source Models](https://mlsanity.com/paper/2508.12461/) (2025)
- [Multi-Agent Medical Decision Consensus Matrix System: An Intelligent Collaborative Framework for Oncology MDT Consultations](https://mlsanity.com/paper/2512.14321/) (2025)
- [SuperFlow: Training Flow Matching Models with RL on the Fly](https://mlsanity.com/paper/2512.17951/) (2025)
- [Abductive Inference in Retrieval-Augmented Language Models: Generating and Validating Missing Premises](https://mlsanity.com/paper/2511.04020/) (2025)
- [Towards Better Evaluation for Generated Patent Claims](https://mlsanity.com/paper/2505.11095/) (2025)
- [CenterMamba-SAM: Center-Prioritized Scanning and Temporal Prototypes for Brain Lesion Segmentation](https://mlsanity.com/paper/2511.01243/) (2025)
- [LLM-Driven Adaptive Source-Sink Identification and False Positive Mitigation for Static Analysis](https://mlsanity.com/paper/2511.04023/) (2025)
- [Hybrid Fuzzing with LLM-Guided Input Mutation and Semantic Feedback](https://mlsanity.com/paper/2511.03995/) (2025)
- [TV-RAG: A Temporal-aware and Semantic Entropy-Weighted Framework for Long Video Retrieval and Understanding](https://mlsanity.com/paper/2512.23483/) (2025)
- [Enriching Patent Claim Generation with European Patent Dataset](https://mlsanity.com/paper/2505.12568/) (2025)
- [Free-Mask: A Novel Paradigm of Integration Between the Segmentation Diffusion Model and Image Editing](https://mlsanity.com/paper/2411.01819/) (2024)

## Abstract (arXiv)

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.