English
Related papers

Related papers: LLM-based Triplet Extraction from Financial Report…

200 papers

The rapid expansion of publicly-available medical data presents a challenge for clinicians and researchers alike, increasing the gap between the volume of scientific literature and its applications. The steady growth of studies and findings…

Artificial Intelligence · Computer Science 2025-08-06 Taine J. Elliott , Stephen P. Levitt , Ken Nixon , Martin Bekker

Knowledge base population seeks to expand knowledge graphs with facts that are typically extracted from a text corpus. Recently, language models pretrained on large corpora have been shown to contain factual knowledge that can be retrieved…

Computation and Language · Computer Science 2024-01-30 Andrés García-Silva , Cristian Berrío , José Manuel Gómez-Pérez

Large Language Models (LLMs) have shown impressive capability in language generation and understanding, but their tendency to hallucinate and produce factually incorrect information remains a key limitation. To verify LLM-generated contents…

Computation and Language · Computer Science 2025-06-03 Kushan Mitra , Dan Zhang , Sajjadur Rahman , Estevam Hruschka

Single document news summarization has seen substantial progress on faithfulness in recent years, driven by research on the evaluation of factual consistency, or hallucinations. We ask whether these advances carry over to other text…

This study investigates the effectiveness of Large Language Models (LLMs) for the extraction of structured knowledge in the form of Subject-Predicate-Object triples. We apply the setup for the domain of Economics application. The findings…

Computation and Language · Computer Science 2025-10-08 Durgesh Nandini , Rebekka Koch , Mirco Schoenfeld

Large Language Models (LLMs) demonstrate impressive capabilities in natural language processing but suffer from inaccuracies and logical inconsistencies known as hallucinations. This compromises their reliability, especially in domains…

Artificial Intelligence · Computer Science 2025-12-08 Ruslan Idelfonso Magana Vsevolodovna , Marco Monti

Collecting labeled datasets in finance is challenging due to scarcity of domain experts and higher cost of employing them. While Large Language Models (LLMs) have demonstrated remarkable performance in data annotation tasks on general…

Computation and Language · Computer Science 2024-03-28 Toyin Aguda , Suchetha Siddagangappa , Elena Kochkina , Simerjot Kaur , Dongsheng Wang , Charese Smiley , Sameena Shah

LLMs obtain remarkable performance but suffer from hallucinations. Most research on detecting hallucination focuses on the questions with short and concrete correct answers that are easy to check the faithfulness. Hallucination detections…

Computation and Language · Computer Science 2025-03-10 Xinyue Fang , Zhen Huang , Zhiliang Tian , Minghui Fang , Ziyi Pan , Quntian Fang , Zhihua Wen , Hengyue Pan , Dongsheng Li

Large language model (LLM)-based AI agents are increasingly deployed in manufacturing environments for analytics, quality management, and decision support. These agents demonstrate statistical fluency with domain terminology but lack…

Artificial Intelligence · Computer Science 2026-05-13 Grama Chethan

While Large Language Models (LLMs) demonstrate exceptional performance in a multitude of Natural Language Processing (NLP) tasks, they encounter challenges in practical applications, including issues with hallucinations, inadequate…

Computation and Language · Computer Science 2024-06-13 Yihao Li , Ru Zhang , Jianyi Liu

The project, under industrial funding, presented in this publication aims at the semantic analysis of a normative document describing requirements applicable to electrical appliances. The objective of the project is to build a semantic…

Information Retrieval · Computer Science 2021-12-28 Helene de Ribaupierre , Anne-Francoise Cutting-Decelle , Nathalie Baumier , Serge Blumental

The use of large language models (LLMs) has significantly increased since the introduction of ChatGPT in 2022, demonstrating their value across various applications. However, a major challenge for enterprise and commercial adoption of LLMs…

Computation and Language · Computer Science 2024-08-28 N. E. Kriman

Relational fact extraction aims to extract semantic triplets from unstructured text. In this work, we show that all of the relational fact extraction models can be organized according to a graph-oriented analytical perspective. An efficient…

Computation and Language · Computer Science 2021-06-04 Fubang Zhao , Zhuoren Jiang , Yangyang Kang , Changlong Sun , Xiaozhong Liu

We present a solver-agnostic framework in which coordinated large language model (LLM) agents autonomously execute the complete computational mechanics workflow, from perceptual data of an engineering component through geometry extraction,…

Computational Engineering, Finance, and Science · Computer Science 2026-04-14 Daniel N. Wilke

Current methods for embedding-based query answering over incomplete Knowledge Graphs (KGs) only focus on inductive reasoning, i.e., predicting answers by learning patterns from the data, and lack the complementary ability to do deductive…

Artificial Intelligence · Computer Science 2023-09-01 Medina Andresel , Trung-Kien Tran , Csaba Domokos , Pasquale Minervini , Daria Stepanova

Language models exhibit fundamental limitations -- hallucination, brittleness, and lack of formal grounding -- that are particularly problematic in high-stakes specialist fields requiring verifiable reasoning. I investigate whether formal…

Artificial Intelligence · Computer Science 2026-02-23 Marcelo Labre

[Background]: Systematic Literature Review (SLR) has become an important software engineering research method but costs tremendous efforts. [Aim]: This paper proposes an approach to leverage on empirically evolved ontology to support…

Digital Libraries · Computer Science 2016-09-27 Yueming Sun , Ye Yang , He Zhang , Wen Zhang , Qing Wang

LLMs deployed for natural-language querying of analytical databases suffer from two intertwined failures - incorrect answers and confident hallucinations - both rooted in the same cause: the model is forced to infer business semantics that…

Artificial Intelligence · Computer Science 2026-04-29 Michael Rumiantsau , Ivan Fokeev

Large language models (LLMs) are notorious for hallucinating, i.e., producing erroneous claims in their output. Such hallucinations can be dangerous, as occasional factual inaccuracies in the generated text might be obscured by the rest of…

Financial sentiment analysis is critical for valuation and investment decision-making. Traditional NLP models, however, are limited by their parameter size and the scope of their training datasets, which hampers their generalization…

Computation and Language · Computer Science 2023-11-07 Boyu Zhang , Hongyang Yang , Tianyu Zhou , Ali Babar , Xiao-Yang Liu