Despite the power of Large Language Models (LLMs) like GPT-4, they still struggle with
tasks that require generating complex, structured outputs. In this study, we assess the …

This paper introduces PRobELM (Plausibility Ranking Evaluation for Language Models), a
benchmark designed to assess language models' ability to discern more plausible from less …

Large language models can perform well on general natural language tasks, but their
effectiveness is still suboptimal for information extraction (IE). Recent works indicate that the …

We study a new problem setting of question answering (QA), referred to as DocTabQA.
Within this setting, given a long document, the goal is to respond to questions by organizing …

This thesis investigates how natural language understanding and generation with
transformer models can benefit from grounding the models with knowledge representations …

Irregular data in real-world are usually organized as heterogeneous graphs (HGs)
consisting of multiple types of nodes and edges. To explore useful knowledge from real …

Although the advancements of pre-trained Large Language Models have significantly
accelerated recent progress in NLP, their ever-increasing size poses significant challenges …

This six-volume set LNCS 14804-14809 constitutes the proceedings of the 18th International
Conference on Document Analysis and Recognition, ICDAR 2024, held in Athens, Greece …

Abstract Information Extraction (IE) is a core area of natural language processing focused on
identifying structured information, such as named entities and relationships, within plain text …

The field of information retrieval (IR) has evolved significantly with the advent of Generative
Information Retrieval (GenIR) models, which leverage advancements in large language …