OpenSanctions Pairs is the first large‑scale public benchmark for entity matching on sanctions and OSINT data, comprising 755,540 expert‑labeled pairs drawn from over 1 million entities across 293 source datasets and 45 jurisdictions. The dataset spans multiple languages and writing systems, inconsistent structures, and time‑varying provenance, making it far more heterogeneous than prior benchmarks. Baseline experiments show a rule‑based matcher achieving 91.3 % F1, GPT‑4o reaching 99.0 % F1, and a locally deployable open‑source model scoring 98.2 % F1, with complementary failure modes that highlight the need to focus on downstream pipeline components.
By Chandler Smith, Magnus Sesodia, Friedrich Lindenberg, Christian Schroeder de Witt
arXiv:2607. 25579v1 Announce Type: cross Abstract: Entity alignment (EA) identifies entities across knowledge graphs (KGs) that refer to the same real-world object.
By Xinran Liu, Shengtao Li, Shouqian Shi, Ge Wang, Xin-Wei Yao
arXiv:2606. 06109v1 Announce Type: cross Abstract: Entity alignment (EA) aims to identify equivalent entities across heterogeneous knowledge graphs (KGs) and is a key component of knowledge fusion and cross-KG reasoning.
By Xingyu Chen, Yuanning Cui, Zequn Sun, Wei Hu
arXiv:2609.37543v1 Announce Type: new
Abstract: Cross-lingual zero-shot transfer and multilingual fine-tuning are promising approaches for NLP tasks such as Named Entity Recognition (NER) in low-reso...
By Prosper Arineitwe Asiimwe, Francois Meyer, Jan Buys
The paper investigates whether large language models (LLMs) can leverage frozen relational‑transformer embeddings by injecting them as soft tokens. Using a learned MLP projection and LoRA adaptation, the authors fine‑tune Qwen3.5‑4B on chain‑of‑thought reasoning traces and group‑based reinforcement learning, then evaluate on ten binary classification tasks across six RelBench databases. The hybrid approach consistently underperforms the standalone relational transformer, showing sensitivity to serialization format, token budget, and RL stability, leading the authors to conclude that stronger alignment objectives and schema‑aware design are needed for reliable relational prediction.
By Francisco Galuppo Azevedo, Clarissa Lima Loures
arXiv:2601.06347v3 Announce Type: replace
Abstract: Recent progress in universal multilingual named entity recognition (NER) has been driven by multilingual transformer models, task-specific architec...
By Jonas Golde, Patrick Haller, Alan Akbik
arXiv:2606. 31718v1 Announce Type: cross Abstract: Relation extraction (RE) for low-resource languages is typically constrained by the lack of annotated corpora.
By Dragos-Mitrut Vasile, Elena-Simona Apostol, Stefan-Adrian Toma, Adrian Paschke, Ciprian-Octavian Truica
arXiv:2609.24372v1 Announce Type: new
Abstract: In-context learning (ICL) based on large language models (LLMs) has shown promising potential in alleviating performance bottlenecks caused by the limi...
By Jingyu Wang, Shijie Wu, Fusheng Jin
arXiv:2609.13486v1 Announce Type: cross
Abstract: Recent work has shown that fine-tuning decoder-only large language models (LLMs) for retrieval yields strong first-stage retrievers, with effectivene...
By Anubhav Shrestha, Safal Shrestha, Minwu Kim, Torsten Suel, Keith Ross
The paper investigates whether small models distilled from larger ones behave similarly when using byte versus token tokenization. It introduces two methods—Marginalize‑It (approximate) and End‑Of‑Token (exact)—to convert token logits to byte logits, and conducts a large‑scale study on decoder‑only dense transformers ranging from 1 billion to 1 trillion bytes of data. Results show that while token‑based models excel early, byte‑based models eventually surpass them with more compute, achieving higher performance ceilings, greater data efficiency, and lower logit storage costs.
By Kalyani Marathe, Artidoro Pagnoni, Tomasz Limisiewicz, Margaret Li, Mike Lewis, Luke Zettlemoyer, Srinivasan Iyer
The paper investigates modular entity disambiguation by separating candidate retrieval from entity selection. It compares sparse retrieval (BM25), Web KB search, and a dense retriever, all paired with large language model selectors. Results show that a training‑free BM25 retriever combined with an LLM selector achieves state‑of‑the‑art performance on the ZELDA benchmark, and the modular approach enables abstention when retrieval fails.
By Fina Polat, Daniel Daza, Pengyu Zhang, Klim Zaporojets, Paul Groth
The paper compares generative and encoder-based neural models for multilingual Named Entity Recognition (NER) across the eleven languages of the Naamapadam benchmark. Five classic model families, four decoder-only large language models fine‑tuned with LoRA and 4‑bit NF4 quantisation, and nine generative models in zero‑to‑5‑shot inference were evaluated under strict CoNLL span‑level metrics. Encoder-based models (mBERT and XLM‑R) achieved substantially higher F1 scores—up to 0.675 on Hindi—than any generative architecture, with gaps of 7.5–40 percentage points; the best few‑shot result reached only 28% of the encoder baseline. The study identifies three language clusters (encoder‑dominant, partial‑coverage, and failure‑zone) and offers deployment guidelines based on transfer learning and low‑resource NLP principles.
By Jakkala Mahesh, Jatavath Shravan Kumar, Komalla Shivani, Sujoy Sarkar