SOURCE-LINKED INTELLIGENCE

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

arXiv · AI, language, vision and robotics · article · Aug 31, 2026 · UTC

Scientific domain entity linking (EL) differs from general domain EL because mentions and entity names often lack lexical overlap. Another challenge is that specialized terminology is used in the scientific domain, which is rarely encountered in models pretrained on general domains. Therefore, models trained on general domains transfer poorly to scientific domains. To address this, in-domain fine-tuning is the natural remedy. However, many scientific domains lack expert-annotated data, motivating the need for a zero-human-annotation approach. Existing zero-shot methods heavily rely on LLMs to

Read original source ↗ Open in workspace

recordType

paper

region

Global