arXiv Computation and Language

BELXTR: Biomedical Entity Linking via Contextualized Token Retrieval

BELXTR is a new biomedical entity linking model that uses a multi‑vector (late interaction) architecture to preserve token‑level matching information, unlike traditional embedding‑based approaches that compress mentions into a single vector. By extending the XTR model with a task‑specific training objective and active query expansion, BELXTR achieves state‑of‑the‑art performance on half of ten evaluated corpora, with an average 5‑percentage‑point gain in recall@1. The model shows especially strong results on cross‑species gene disambiguation, outperforming an LLM‑powered retrieve‑and‑rerank pipeline and approaching a specialized rule‑based system.

arXiv AI

Sep 3

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

llms rag nlp benchmarks

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

rag benchmarks

arXiv Machine Learning

Aug 4

H+ Embedding: Harmonizing Global and Token-Level Retrieval with Context-Dependent Phrases

arXiv:2608. 00065v1 Announce Type: cross Abstract: Terminology-intensive retrieval, especially in medical settings, depends on preserving multi-word entities, abbreviations, numerical constraints, and compositional concepts.

By Shusen Zhang, Junyi Hu, Ye Feng, Ziteng Wang, Zhaoyuan Pan, Guosheng Dong, Xiaojun Yuan, Jiangshou Hong, Xiangzhi Wang

rag nlp

arXiv Computation and Language

Aug 31

Select, Don't Train: The Benefits of Modular Entity Disambiguation with LLM-Based Selection

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

llms rag benchmarks

arXiv AI

3d ago

Constructing Disambiguated Knowledge Bases from Large Language Models at Scale

arXiv:2608.03729v4 Announce Type: replace-cross Abstract: Automated Knowledge Base Construction (AKBC) is a core NLP task, and recent work proposes generating knowledge bases directly from large lang...

By Yujia Hu, Tuan-Phong Nguyen, Simon Razniewski

llms rag nlp

arXiv AI

Sep 3

Direct Construction of Disambiguated Knowledge Bases from Large Language Models

The paper introduces GPTKB 2.0, a method for building disambiguated knowledge bases directly from large language models. It addresses the lack of native entity representation in LLMs by performing on‑the‑fly disambiguation of entities, relations, and classes, achieving a million‑scale KB with over 1 million disambiguated entities and 38.4 million triples. The authors analyze trade‑offs among accuracy, scale, and cost, and release the system at https://gptkb.org/.

By Yujia Hu, Tuan-Phong Nguyen, Simon Razniewski

llms rag nlp

arXiv Computation and Language

Sep 2

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

arXiv:2609.00228v1 Announce Type: new Abstract: Scientific domain entity linking (EL) differs from general domain EL because mentions and entity names often lack lexical overlap. Another challenge is...

By Md Rasel Khondokar, Qiao Qiao, Farjana Sultana Samia, Nhat Le, Yuepei Li, Qi Li

llms fine-tuning benchmarks

arXiv AI

Aug 5

GPTKB 2.0: Direct Construction of Disambiguated Knowledge Bases from Large Language Models

arXiv:2608. 03729v1 Announce Type: cross Abstract: Automated Knowledge Base Construction (AKBC) is a core NLP task, and recent work proposes generating knowledge bases directly from large language models (LLMs), treating the model itself as the knowledge source.

By Yujia Hu, Tuan-Phong Nguyen, Simon Razniewski

llms rag nlp

arXiv AI

Aug 24

EnSI-RAG: Entity-Structure-Indexed Retrieval-Augmented Generation for Long-Document Question Answering

arXiv:2608.21252v1 Announce Type: cross Abstract: Question answering (QA) over long, connected documents remains challenging because relevant evidence may span multiple entities and their relationshi...

By Xuanyu Meng, Jiashuo Sun, Jash Rajesh Parekh, Jiawei Han

llms rag nlp

arXiv AI

Jun 16

Few-Shot Biomedical Relation Extraction with Large Language Models: A Viable Alternative to Supervised Learning?

arXiv:2606. 15412v1 Announce Type: cross Abstract: Biomedical relation extraction (BioRE) is a key step in transforming biomedical literature into structured knowledge.

By Jakob Mraz, Toma\v{z} Curk, Bla\v{z} Zupan

llms

arXiv AI

Aug 10

GPTKB 2.0: Browsing, Querying, and Auditing a Disambiguated LLM-Derived Knowledge Base

arXiv:2608. 06992v1 Announce Type: cross Abstract: We present a web demo for exploring a large-scale disambiguated knowledge base (KB) materialized from a large language model (LLM).

By Yujia Hu, Tuan-Phong Nguyen, Simon Razniewski

llms rag

arXiv AI

Aug 21

Automatic bioinformatic software named entity recognition from literature

arXiv:2608. 19201v1 Announce Type: cross Abstract: Bioinformatics software and databases are essential components of modern life science research, yet their mentions in the scientific literature are often inconsistent and difficult to systematically identify at scale.

By Hao Xuan, Rithvij Pasupuleti, Ben Liu, Haishuo Sun, Jun Zhang, Zijun Yao, Cuncong Zhong

llms rag nlp efficiency benchmarks

Related stories