arXiv:2511. 10657v2 Announce Type: replace-cross Abstract: We study self-supervised patent representation learning with contrastive objectives.
arXiv:2605.10073v3 Announce Type: replace Abstract: Pre-trained language models advance patent classification and retrieval by encoding claims as flat token sequences, but they overlook the dependenc...
arXiv:2609.36550v1 Announce Type: new Abstract: Retrieval-augmented generation is widely used in professional writing, yet whether retrieval grounds revision or merely injects templates is rarely tes...
arXiv:2608.21924v1 Announce Type: new Abstract: Patent litigation imposes substantial costs on firms and distorts R&D incentives, making early risk identification a practically important task. While...
SciTBERT is a family of BERT-derived language models trained on chronologically consistent corpora of scientific papers, patents, and educational web text, with training cutoffs spanning 2013 to 2025. The models are further post‑trained using paper and patent citations to create the SciTBERT‑CI family, which better captures temporal dynamics. Experiments show that these chronologically consistent encoders outperform earlier domain‑specific models, especially when training data is limited by early year restrictions, and they perform well on the new PatRepEval benchmark of patent‑related tasks at the science‑technology interface.
DECSELFMASK is a decoder‑only classification method that uses unlabeled clinical text to improve performance. It creates self‑supervised training examples by masking portions of the text identified as relevant through relevance attribution, then trains the model to reconstruct the masked tokens via next‑token prediction. Experiments on 136 tasks from 1.9 M Italian hospital notes show consistent gains across five models, outperforming base models (+9.1 Macro F1), continual pretraining (+6.3), and synthetic label generation (+12.5).
arXiv:2608.29899v1 Announce Type: cross Abstract: Dense retrieval over long documents is expensive. Token-level encoders scale quadratically in sequence length, and most long-context embedding models...
Sparse Coverage is an unsupervised semantic retrieval framework designed for patent prior‑art search. It maps local span embeddings to a sparse vocabulary of embedding‑space centers chosen via a coverage‑oriented k‑center objective, allowing spans to activate nearby centers and produce sparse representations that work with inverted‑index retrieval. Experiments on CLEF‑IP 2013 demonstrate that Sparse Coverage matches or surpasses dense patent encoders in document‑level recall while remaining competitive at the passage level, making it an effective first‑stage retrieval approach for patent search.
arXiv:2606. 02814v1 Announce Type: cross Abstract: Neural retrievers are trained to estimate query-document relevance from annotated query-document pairs.
arXiv:2604. 19047v2 Announce Type: replace-cross Abstract: Existing QA benchmarks typically assume distinct documents with minimal overlap, yet real-world retrieval-augmented generation (RAG) systems operate on corpora such as financial reports, legal codes, and patents, where information is highly redundant and documents exhibit strong inter-document similarity.
The paper evaluates unsupervised embedding geometries for patent claim classification, comparing hyperbolic and Euclidean Variational Autoencoders trained on 45,000 US patents. Hyperbolic embeddings retrieve cross-category prior art 52% more often than Euclidean embeddings (18.76% vs. 12.34% of top‑10 results across 3,000 queries). The study also links classification breadth and patents per subgroup to model performance, offering a practical signal for when the method is most useful.
arXiv:2609.23231v1 Announce Type: new Abstract: Cross-lingual information retrieval (CLIR) is increasingly important in multi-national industries, where critical technical evidence may exist in a dif...
BLANC (Blank Landscape Analysis through NPMI Conditioning) is a three‑phase pipeline that uses multi‑view neural topic modeling across application/use, novelty, and inventive step, computes Normalized Pointwise Mutual Information (NPMI) to measure cross‑dimensional cluster association, and introduces a conditional detection step that flags combinations whose NPMI drops when the corpus is filtered by a keyword. The drop is quantified by a new metric, ΔNPMI, which identifies combinations that are established globally but unexplored locally. BLANC was evaluated on two USPTO corpora—machine learning/AI and glass compositions—by artificially depleting known technology combinations; it recovered 34.1% and 27.3% of the depleted pairs, respectively, while random removals rarely recovered the target, and it successfully identified a fluorine surface‑treatment × warpage‑suppression candidate in a proprietary float‑glass case.