# Is It Novel and Why? Fine-Grained Patent Novelty Prediction Based on Passage Retrieval

arXiv: https://arxiv.org/abs/2605.02392 · HTML: https://mlsanity.com/paper/2605.02392/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 65 references that are in the map.
- First posted on arXiv 4 May 2026.

## Builds on (most cited first, 26 of 26)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs](https://mlsanity.com/paper/2402.03927/) (2024)
- [Adversarial Filters of Dataset Biases](https://mlsanity.com/paper/2002.04108/) (2020)
- [Investigating Data Contamination in Modern Benchmarks for Large Language Models](https://mlsanity.com/paper/2311.09783/) (2023)
- [MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing](https://mlsanity.com/paper/2509.22186/) (2025)
- [An Open Source Data Contamination Report for Large Language Models](https://mlsanity.com/paper/2310.17589/) (2023)
- [Evaluating and Enhancing Large Language Models for Novelty Assessment in Scholarly Publications](https://mlsanity.com/paper/2409.16605/) (2024)
- [Natural Language Processing in the Patent Domain: A Survey](https://mlsanity.com/paper/2403.04105/) (2024)
- [A review on the novelty measurements of academic papers](https://mlsanity.com/paper/2501.17456/) (2025)
- [A Survey on Patent Analysis: From NLP to Multimodal AI](https://mlsanity.com/paper/2404.08668/) (2024)
- [Pap2Pat: Benchmarking Outline-Guided Long-Text Patent Generation with Patent-Paper Pairs](https://mlsanity.com/paper/2410.07009/) (2024)
- [SC4ANM: Identifying Optimal Section Combinations for Automated Novelty Prediction in Academic Papers](https://mlsanity.com/paper/2505.16330/) (2025)
- [An automatic patent literature retrieval system based on LLM-RAG](https://mlsanity.com/paper/2508.14064/) (2025)
- [PANORAMA: A Dataset and Benchmarks Capturing Decision Trails and Rationales in Patent Examination](https://mlsanity.com/paper/2510.24774/) (2025)
- [NovAScore: A New Automated Metric for Evaluating Document Level Novelty](https://mlsanity.com/paper/2409.09249/) (2024)
- [EvoPat: A Multi-LLM-based Patents Summarization and Analysis Agent](https://mlsanity.com/paper/2412.18100/) (2024)
- [Enhancing the Patent Matching Capability of Large Language Models via the Memory Graph](https://mlsanity.com/paper/2504.14845/) (2025)
- [PatentEdits: Framing Patent Novelty as Textual Entailment](https://mlsanity.com/paper/2411.13477/) (2024)
- [Can AI Examine Novelty of Patents?: Novelty Evaluation Based on the Correspondence between Patent Claim and Prior Art](https://mlsanity.com/paper/2502.06316/) (2025)
- [PEDANTIC: A Dataset for the Automatic Examination of Definiteness in Patent Claims](https://mlsanity.com/paper/2505.21342/) (2025)
- [Pat-DEVAL: Chain-of-Legal-Thought Evaluation for Patent Description](https://mlsanity.com/paper/2601.00166/) (2026)
- [ClaimCompare: A Data Pipeline for Evaluation of Novelty Destroying Patent Pairs](https://mlsanity.com/paper/2407.12193/) (2024)
- [Structural Representation Learning and Disentanglement for Evidential Chinese Patent Approval Prediction](https://mlsanity.com/paper/2408.12852/) (2024)

## Built on by (most cited first, 1 of 1)

- [Benchmarking Patent Drafting from Inventor-Style Disclosures](https://mlsanity.com/paper/2608.21249/) (2026)

## Abstract (arXiv)

Novelty assessment is a critical yet complex task in the examination process for patent acceptance, requiring examiners to determine whether an invention is disclosed in a prior art document. The process involves intricate matching between specific features of a patent claim and passages in the prior art. While prior work has approached novelty prediction primarily as a binary classification task at the claim level, we argue that this formulation is susceptible to spurious correlations and lacks the granularity required for practical application. In this work, we introduce FiNE-Patents (Fine-grained Novelty Examination of Patents), a novel dataset comprising 3,658 first patent claims annotated with fine-grained, feature-level prior art references extracted from European Search Opinion (ESOP) documents. We propose shifting the evaluation paradigm from simple binary classification to a joint retrieval and abstract reasoning task at the feature level, requiring models to identify specific passages from a prior art document that disclose individual claim features, and to identify which features of a claim make it novel. We implement and evaluate LLM-based workflows that decompose claims into features, analyze each feature against prior art, and finally derive a claim-level novelty prediction. Our experiments demonstrate that these workflows outperform embedding-based baselines on passage retrieval and novel feature identification. Furthermore, we show that unlike trained classifiers, LLMs are robust against spurious correlations present in the claim-level novelty classification task. We release the dataset and code to foster further research into transparent and granular patent analysis.