arXiv Computation and Language

Bridging Lexical Divergence: LLM-Assisted, Cost-Efficient, Zero-shot Scientific Entity Linking

arXiv AI
1d ago

BioELX: Context-Aware Cross-lingual Biomedical Entity Linking without Task-Specific Supervision

BioELX is a retrieve‑rerank framework for cross‑lingual biomedical entity linking that tackles two key problems: the English‑biased UMLS alias training data and the degradation caused by naïvely adding context. It fine‑tunes SapBERT_multi with Wikidata‑derived cross‑lingual alias supervision to create shared concept neighborhoods, and then reranks candidates using pretrained LLMs with mention‑anchored prompting to focus on the target mention. Experiments demonstrate state‑of‑the‑art performance on four benchmarks, improving Recall@1 by 4.8–18.2 percentage points without task‑specific annotations.

By Yi Wang, Corina Dima, Liangyu Zhong, Steffen Staab
arXiv Machine Learning
Aug 6

Neighborhood-Aware Dual Biomedical Entity Linking

arXiv:2608. 04144v1 Announce Type: cross Abstract: Biomedical entity linking grounds mentions in clinical and scientific text to entities in a curated knowledge base (KB) with ontological structure, which supports downstream applications such as literature-scale information extraction and patient-record normalization.

By Yicheng Tao, Jie Liu
arXiv Computation and Language
Aug 25

LakeHopper: Knowledge-Aware Adaptation of Column Type Annotators across Data Lakes

LakeHopper is a method for adapting column type annotators (CTA) from one data lake to another by treating cross‑lake adaptation as a knowledge‑management problem. It decomposes the source annotator’s knowledge into source‑specific, shared, and target‑specific parts, and then uses three mechanisms—label‑set realignment, LLM‑verified gap discovery, and cluster‑based propagation with rehearsal fine‑tuning—to adapt the annotator under a limited annotation budget. The approach achieves up to a 71.4% relative macro‑F1 improvement over three PLM backbones, reaches near‑full data quality with less than 6% of target labels, and trains 27–131 times faster than fine‑tuned table LLMs.

By Yushi Sun, Xujia Li, Nan Tang, Quanqing Xu, Chuanhui Yang, Lei Chen
arXiv Computation and Language
3d ago

Error-Type-Aware Loss Reweighting for Robust Named Entity Recognition with Noisy LLM Labels

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 AI
Jun 18

Improving Scientific Document Retrieval with Academic Concept Index

arXiv:2601. 00567v2 Announce Type: replace-cross Abstract: Adapting general-domain retrievers to scientific domains is challenging due to the scarcity of large-scale domain-specific relevance annotations and the substantial mismatch in vocabulary and information needs.

By Jeyun Lee, Junhyoung Lee, Wonbin Kweon, Bowen Jin, Yu Zhang, Susik Yoon, Dongha Lee, Hwanjo Yu, Jiawei Han, Seongku Kang
arXiv Computation and Language
Aug 27

Just Pass Twice: Efficient Token Classification with LLMs for Zero-Shot NER

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