Large language models (LLMs) are increasingly used to annotate datasets for training smaller, task‑specialized models such as named entity recognition (NER). However, current fine‑tuning processes ignore the annotation noise introduced by LLMs, leading to degraded performance, and existing noise‑robust losses fail to handle the heterogeneous nature of NER noise (e.g., missing mentions vs. type errors). The authors propose error‑type‑aware loss reweighting, which applies separate reweighting rules for different erroneous token types, improving F1 scores by 0.8–2.0 percentage points on average and up to 4.6 points on Wikigold at 24.1% noise.
By Elena Merdjanovska, Jonas Golde, Alan Akbik
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. 10392v1 Announce Type: new Abstract: Financial named-entity recognition (NER) is essential for translating unstructured financial reports and news into structured knowledge graphs.
By Wu Yuerong, Mingni Luo
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
The paper introduces Iterative MBR Distillation for Error Span Detection (ESD) in machine translation, a self‑evolution framework that replaces human annotations with pseudo‑labels generated by a large language model. By iteratively applying Minimum Bayes Risk decoding, the method produces high‑quality error spans without costly human effort. Experiments on WMT Metrics Shared Task datasets show that models trained solely on these pseudo‑labels outperform both unadapted baselines and supervised models trained on human data at system and span levels, while keeping sentence‑level performance competitive.
By Boxuan Lyu, Haiyue Song, Zhi Qu
arXiv:2410.17355v4 Announce Type: replace
Abstract: Due to their capacity to acquire world knowledge from large corpora, pre-trained language models (PLMs) are extensively used in ultra-fine entity t...
By Advait Deshmukh, Ashwin Umadi, Dananjay Srinivas, Maria Leonor Pacheco
arXiv:2602.14488v3 Announce Type: replace-cross
Abstract: IR in low-resource languages remains limited by the scarcity of high-quality, task-specific annotated datasets. Manual annotation is expensiv...
By Md. Najib Hasan, Mst. Jannatun Ferdous Rain, Fyad Mohammed, Nazmul Siddique
arXiv:2606. 05444v1 Announce Type: cross Abstract: Coreference resolution is a core NLP task, having a broad range of downstream applications, e.
By Adriana-Valentina Costache, Eduard Poesina, Silviu-Florin Gheorghe, Paul Irofti, Radu Tudor Ionescu
arXiv:2608.29890v1 Announce Type: new
Abstract: Biomedical Named Entity Recognition (NER) is fundamental to healthcare AI applications, including clinical decision support and medical information ext...
By Nhu Vo, Phuong Nguyen, Nu Uyen Phuong Le, Inigo Jauregi Unanue, Dung D. Le, Massimo Piccardi, Wray Buntine
LuxIT is a monolingual instruction‑tuning dataset for Luxembourgish, created by synthesizing instruction‑answer pairs from native texts using the DeepSeek‑R1‑0528 model and a quality‑assurance LLM‑as‑judge process. The resulting 227,507 high‑quality pairs were used to fine‑tune 14 LLMs (≤15 B parameters), yielding an average accuracy increase of +5.37 percentage points on standardized Luxembourgish proficiency exams and improvements in macro‑averaged F1 on nine of the fourteen downstream NLP tasks. These findings demonstrate that synthetic monolingual data can effectively enhance LLM performance in low‑resource languages and reveal the complex relationship between exam performance and practical NLP gains.
By Julian Valline, Cedric Lothritz, Siwen Guo, Jordi Cabot
The paper introduces NegCue, a large-scale dataset of 1.8 million samples that includes single-word, multi-word, and affixal negation cues, totaling over 200 unique forms. The authors pre-train encoder-only language models and large language models on this dataset to study how different negation types influence understanding. Experiments on five downstream benchmarks reveal that affixal negations provide the most significant performance gains, whereas single-word negations yield modest improvements, and that additional pre-training benefits both model types.
By Tian Tan, Eduardo Blanco
Just Pass Twice (JPT) is a method that allows causal large language models to perform token classification for zero‑shot named entity recognition by concatenating the input with itself, giving each token full bidirectional context without architectural changes. The approach combines these representations with definition‑guided entity embeddings to enable flexible zero‑shot generalization. JPT achieves state‑of‑the‑art results, outperforming prior methods by an average of +7.9 F1 on CrossNER and MIT benchmarks and running over 20× faster than comparable generative approaches.
By Ahmed Ewais, Ahmed Hashish, Amr Ali