Citation-Driven Multi-View Training for Patent Embeddings: QaECTER and Sophia-Bench

• URL: http://arxiv.org/abs/2604.22897v1
• Date: Fri, 24 Apr 2026 12:18:00 GMT
• Title: Citation-Driven Multi-View Training for Patent Embeddings: QaECTER and Sophia-Bench
• Abstract summary: We introduce Sophiabench, a large-scale patent retrieval benchmark.<n>We also introduce QaECTER, a compact embedding model trained on patent citation graphs.<n>Both benchmarks are designed for practical deployment in large-scale patent search systems.
• Score: 1.7299359373305296
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Patent retrieval underpins critical decisions in innovation, examination, and IP strategy, yet progress has been hampered by the absence of benchmarks that reflect the diversity of real world search scenarios. We address this gap with two contributions. First, we introduce Sophiabench, a large-scale patent retrieval benchmark comprising 10,000 queries and 75,000 corpus documents stratified across ten years, eight IPC technology sections, and twelve filing jurisdictions. Unlike prior benchmarks, Sophia-bench tests retrieval using 12 different query types-from structured patent fields to AI-generated summaries-and evaluates results against citation-based ground truth enhanced with a novel domain-relevance metric (InScope). Together, these enable systematic measurement of how well models perform across query types, technology domains, and jurisdictions. Second, we introduce QaECTER, a 344M-parameter embedding model trained on patent citation graphs and multi-view self-alignment. Despite its compact size, QaECTER establishes a new state of the art for patent retrieval. It outperforms the \#1 model on the English retrieval text embedding benchmark (RTEB), a model 23x larger, as well as all existing patent specific models across every query type, IPC section, and jurisdiction on Sophia-bench, with gains of up to 7.2% average NDCG@10 over the next-best model. These results are confirmed on an independent external benchmark, where QaECTER surpasses all prior models without requiring task-specific instruction prompts. Both the benchmark and the model are designed for practical deployment in large-scale patent search systems.

Related papers

• FormalTCS: Benchmarking End-to-End Frontier Formal Theoretical Computer Science Research of Large Language Models [53.68149869349268]
  Large language models (LLMs) have shown growing potential for automated theoretical computer science (TCS) research.<n>We introduce ourbenchmark, an expert-validated benchmark for evaluating LLMs on frontier, end-to-end TCS research.
  arXiv  Detail & Related papers  (2026-08-20T15:13:41Z)
• PatRe: A Full-Stage Office Action and Rebuttal Generation Benchmark for Patent Examination [22.330452135284414]
  PatRe is the first benchmark that models the full patent examination lifecycle.<n>Our benchmark reframes patent examination as a dynamic, multi-turn process of justification and response.
  arXiv  Detail & Related papers  (2026-05-05T09:42:38Z)
• MultiHaystack: Benchmarking Multimodal Retrieval and Reasoning over 40K Images, Videos, and Documents [57.32877731797049]
  MultiHaystack is the first benchmark designed to evaluate both retrieval and reasoning under large-scale, cross-modal conditions.<n>We find that models perform competitively when provided with the corresponding evidence, but their performance drops sharply when required to retrieve that evidence from the full corpus.
  arXiv  Detail & Related papers  (2026-03-05T21:43:02Z)
• OpenOneRec Technical Report [99.17075873619352]
  OneRec series has successfully unified the fragmented recommendation pipeline into an end-to-end generative framework.<n>OneRec Foundation (1.7B and 8B), a family of models establishing new state-of-the-art (SOTA) results across all tasks in RecIF-Bench.<n>When transferred to the Amazon benchmark, our models surpass the strongest baselines with an average 26.8% improvement in Recall@10 across 10 diverse datasets.
  arXiv  Detail & Related papers  (2025-12-31T10:15:53Z)
• Towards Automated Quality Assurance of Patent Specifications: A Multi-Dimensional LLM Framework [0.5534764384104999]
  Although AI drafting tools have gained prominence in patent writing, the systematic evaluation of AI-generated patent content quality represents a significant research gap.<n>We propose to evaluate patents using regulatory compliance, technical coherence, and figure-reference consistency detection modules.<n>The framework is validated on a comprehensive dataset comprising 80 human-authored and 80 AI-generated patents from two patent drafting tools.
  arXiv  Detail & Related papers  (2025-10-29T11:20:18Z)
• PatenTEB: A Comprehensive Benchmark and Model Family for Patent Text Embedding [1.0742675209112622]
  Patent text embeddings enable prior art search, technology landscaping, and patent analysis, yet existing benchmarks inadequately capture patent-specific challenges.<n>We introduce PatenTEB, a comprehensive benchmark comprising 15 tasks across retrieval, classification, paraphrase, and clustering, with 2.06 million examples.<n>We develop the patembed model family through multi-task training, spanning 67M to 344M parameters with context lengths up to 4096 tokens.
  arXiv  Detail & Related papers  (2025-10-25T12:01:46Z)
• UNIDOC-BENCH: A Unified Benchmark for Document-Centric Multimodal RAG [82.84014669683863]
  Multimodal retrieval-augmented generation (MM-RAG) is a key approach for applying large language models to real-world knowledge bases.<n>UniDoc-Bench is the first large-scale, realistic benchmark for MM-RAG built from 70k real-world PDF pages.<n>Our experiments show that multimodal text-image fusion RAG systems consistently outperform both unimodal and jointly multimodal embedding-based retrieval.
  arXiv  Detail & Related papers  (2025-10-04T04:30:13Z)
• Leveraging Generative Models for Real-Time Query-Driven Text Summarization in Large-Scale Web Search [54.987957691350665]
  Query-Driven Text Summarization (QDTS) aims to generate concise and informative summaries from textual documents based on a given query.<n>Traditional extractive summarization models, based primarily on ranking candidate summary segments, have been the dominant approach in industrial applications.<n>We propose a novel framework to pioneer the application of generative models to address real-time QDTS in industrial web search.
  arXiv  Detail & Related papers  (2025-08-28T08:51:51Z)
• PaECTER: Patent-level Representation Learning using Citation-informed Transformers [0.1957338076370071]
  PaECTER is an open-source document-level encoder specific for patents.<n>We fine-tune BERT for Patents with examiner-added citation information to generate numerical representations for patent documents.<n>PaECTER performs better in similarity tasks than current state-of-the-art models used in the patent domain.
  arXiv  Detail & Related papers  (2024-02-29T18:09:03Z)
• How Does Generative Retrieval Scale to Millions of Passages? [68.98628807288972]
  We conduct the first empirical study of generative retrieval techniques across various corpus scales. We scale generative retrieval to millions of passages with a corpus of 8.8M passages and evaluating model sizes up to 11B parameters. While generative retrieval is competitive with state-of-the-art dual encoders on small corpora, scaling to millions of passages remains an important and unsolved challenge.
  arXiv  Detail & Related papers  (2023-05-19T17:33:38Z)
• A Survey on Sentence Embedding Models Performance for Patent Analysis [0.0]
  We propose a standard library and dataset for assessing the accuracy of embeddings models based on PatentSBERTa approach. Results show PatentSBERTa, Bert-for-patents, and TF-IDF Weighted Word Embeddings have the best accuracy for computing sentence embeddings at the subclass level.
  arXiv  Detail & Related papers  (2022-04-28T12:04:42Z)
• Deep learning-based citation recommendation system for patents [5.376388266200792]
  We present a novel dataset called PatentNet that includes textual information and metadata for approximately 110,000 patents from the Google Big Query service. Compared with existing recommendation methods, the proposed benchmark method achieved a mean reciprocal rank of 0.2377 on the test set.
  arXiv  Detail & Related papers  (2020-10-21T12:18:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.