Large language models (LLMs) are a special class of pretrained language models (PLMs)
obtained by scaling model size, pretraining corpus and computation. LLMs, because of their …

Information extraction (IE) aims to extract structural knowledge (such as entities, relations,
and events) from plain natural language texts. Recently, generative Large Language Models …

The goal of temporal relation extraction is to infer the temporal relation between two events
in the document. Supervised models are dominant in this task. In this work, we investigate …

Scientific documents serve as an essential mediator for research achievements and
scientific knowledge. With the increasing availability of full-text data and advanced data …

This study is dedicated to evaluating the capabilities of advanced large language models
(LLMs) such as GPT-3.5-Turbo, GPT-4, and GPT-4-Turbo in the extraction of structured …

This article examines the impact of Artificial Intelligence on the archival heritage digitization
processes, specifically regarding the manuscripts' automatic transcription, their correction …

ABSTRACT As Natural Language Processing (NLP) continues to advance, driven by the
emergence of sophisticated large language models such as ChatGPT, there has been a …

The efficacy of large-scale language models (LLMs) as few-shot learners has dominated the
field of natural language processing, achieving state-of-the-art performance in most tasks …

The digitization of public services in Germany is always based on a legal basis (eg, laws). In
the digitization process, first relevant entities in law documents (eg, actors) are detected …

Since ChatGPT offers detailed responses without justifications, and erroneous facts even for
popular persons, events and places, in this paper we present a novel pipeline that retrieves …