Natural Language Processing Based on Neural Networks and Large Language Models

A special issue of Electronics (ISSN 2079-9292). This special issue belongs to the section "Computer Science & Engineering".

Deadline for manuscript submissions: 30 June 2026 | Viewed by 7476

Special Issue Editors


E-Mail Website
Guest Editor

E-Mail Website
Guest Editor
Computer Vision and Intelligent Perception Lab, School of Computer Science, University of Nottingham Ningbo China, Ningbo 315100, China
Interests: deep-learning-based research for human behavious recognition; human counting and density estimation; tiny object detection; biomedical applications; saliency detection; natural language processing; cybersecurity; face and face expression recognition; road sign detection; license plate recognition

Special Issue Information

Dear Colleagues,

We are excited to announce the launch of a new Special Issue entitled ‘Natural Language Processing Based on Neural Networks and Large Language Models’ in the journal Electronics. This Special Issue aims to explore the transformative impact of neural networks (NNs) and large language models (LLMs) on the field of natural language processing (NLP), highlighting advancements that are redefining the way machines understand and generate human language.

Natural language processing (NLP) has experienced a revolutionary shift with the advent of neural networks (NNs) and large language models (LLMs). These technologies enable advanced applications such as machine translation, sentiment analysis, and conversational agents. This Special Issue focuses on the latest advancements in NN- and LLM-based NLP, addressing challenges in scalability, efficiency, and ethical use, while showcasing innovative methodologies and real-world applications.

This Special Issue will delve into cutting-edge applications and methodologies leveraging NNs and LLMs for NLP, covering topics such as machine translation, conversational AI, sentiment analysis, text generation, and beyond.

We welcome original research, review articles, and case studies that explore the theoretical foundations, algorithmic innovations, and practical implementations of NNs and LLMs in NLP. Special emphasis will be placed on topics such as improving model efficiency, scalability, interpretability, and ethical concerns in AI development.

This Special Issue seeks to bridge gaps in the existing literature by providing a platform for novel ideas and multidisciplinary approaches to NLP. With rapid advancements in NN and LLM technologies, this collection will offer a timely and comprehensive perspective on their evolving role in solving complex linguistic challenges across diverse domains.

While existing research has extensively explored traditional NLP approaches, the rapid development of NN and LLM technologies introduces new challenges and opportunities. This Special Issue will provide an invaluable supplement to the current literature by achieving the following:

  • Showcasing innovative methods that address the limitations of earlier NLP techniques.
  • Discussing the practical implications of NN- and LLM-based solutions in real-world applications.
  • Addressing ethical and societal considerations that arise with the deployment of large-scale language models.

We invite you to submit your latest research to contribute to this exciting field.

Dr. Krzysztof Wolk
Prof. Dr. Xiangjian He
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Electronics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • natural language processing (NLP)
  • neural networks (NN)
  • large language models (LLM)
  • machine translation
  • sentiment analysis
  • conversational artificial intelligence
  • deep learning
  • ethical artificial intelligence
  • text generation
  • computational linguistics

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.

Further information on MDPI's Special Issue policies can be found here.

Published Papers (7 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

32 pages, 678 KB  
Article
The IDRE Dataset in Practice: Training and Evaluation of Small-to-Medium-Sized LLMs for Empathetic Rephrasing
by Simone Manai, Laura Gemme, Roberto Zanoli and Alberto Lavelli
Electronics 2025, 14(20), 4052; https://doi.org/10.3390/electronics14204052 - 15 Oct 2025
Viewed by 173
Abstract
Integrating emotional intelligence into AI systems is essential for developing empathetic chatbots, yet deploying fully empathetic models is often constrained by business, ethical, and computational factors. We propose an innovative solution: a dedicated empathy rephrasing layer that operates downstream of a chatbot’s initial [...] Read more.
Integrating emotional intelligence into AI systems is essential for developing empathetic chatbots, yet deploying fully empathetic models is often constrained by business, ethical, and computational factors. We propose an innovative solution: a dedicated empathy rephrasing layer that operates downstream of a chatbot’s initial response. This layer leverages large language models (LLMs) to infuse empathy into the chatbot’s output without altering its core meaning, thereby enhancing emotional intelligence and user engagement. To implement this layer, we extend and validate the IDRE (Italian Dialogue for Empathetic Responses) dataset. We evaluated small- and medium-scale LLMs across three configurations: baseline models, models augmented via few-shot learning with IDRE exemplars, and models fine-tuned on IDRE. Performance was quantitatively assessed using the LLM-as-a-judge paradigm, leveraging custom metrics. These results were further validated through an independent human evaluation and supported by established NLP similarity metrics, ensuring a robust triangulation of findings. Results confirm that both few-shot prompting and fine-tuning with IDRE significantly enhance the models’ capacity for empathetic language generation. Applications include empathetic AI in healthcare, such as virtual assistants for patient support, and demonstrate promising generalization to other domains. All datasets, prompts, fine-tuned models, and scripts are publicly available to ensure transparency and reproducibility. Full article
Show Figures

Figure 1

18 pages, 2116 KB  
Article
A Markov Chain Replacement Strategy for Surrogate Identifiers: Minimizing Re-Identification Risk While Preserving Text Reuse
by John D. Osborne, Andrew Trotter, Tobias O’Leary, Chris Coffee, Micah D. Cochran, Luis Mansilla-Gonzalez, Akhil Nadimpalli, Alex McAnnally, Abdulateef I. Almudaifer, Jeffrey R. Curtis, Salma M. Aly and Richard E. Kennedy
Electronics 2025, 14(19), 3945; https://doi.org/10.3390/electronics14193945 - 6 Oct 2025
Viewed by 703
Abstract
“Hiding in Plain Sight” (HIPS) strategies for Personal Health Information (PHI) replace PHI with surrogate values to hinder re-identification attempts. We evaluate three different HIPS strategies for PHI replacement, a standard Consistent replacement strategy, a Random replacement strategy, and a novel Markov model [...] Read more.
“Hiding in Plain Sight” (HIPS) strategies for Personal Health Information (PHI) replace PHI with surrogate values to hinder re-identification attempts. We evaluate three different HIPS strategies for PHI replacement, a standard Consistent replacement strategy, a Random replacement strategy, and a novel Markov model strategy. We evaluate the privacy-preserving benefits and relative utility for information extraction of these strategies on both a simulated PHI distribution and real clinical corpora from two different institutions using a range of false negative error rates (FNER). The Markov strategy consistently outperformed the Consistent and Random substitution strategies on both real data and in statistical simulations. Using FNER ranging from 0.1% to 5%, PHI leakage at the document level could be reduced from 27.1% to 0.1% and from 94.2% to 57.7% with the Markov strategy versus the standard Consistent substitution strategy, at 0.1% and 0.5% FNER, respectively. Additionally, we assessed the generated corpora containing synthetic PHI for reuse using a variety of information extraction methods. Results indicate that modern deep learning methods have similar performance on all strategies, but older machine learning techniques can suffer from the change in context. Overall, a Markov surrogate generation strategy substantially reduces the chance of inadvertent PHI release. Full article
Show Figures

Figure 1

20 pages, 776 KB  
Article
Who Speaks to Whom? An LLM-Based Social Network Analysis of Tragic Plays
by Aura Cristina Udrea, Stefan Ruseti, Laurentiu-Marian Neagu, Ovio Olaru, Andrei Terian and Mihai Dascalu
Electronics 2025, 14(19), 3847; https://doi.org/10.3390/electronics14193847 - 28 Sep 2025
Viewed by 272
Abstract
The study of dramatic plays has long relied on qualitative methods to analyze character interactions, making little assumption about the structural patterns of communication involved. Our approach bridges NLP and literary studies, enabling scalable, data-driven analysis of interaction patterns and power structures in [...] Read more.
The study of dramatic plays has long relied on qualitative methods to analyze character interactions, making little assumption about the structural patterns of communication involved. Our approach bridges NLP and literary studies, enabling scalable, data-driven analysis of interaction patterns and power structures in drama. We propose a novel method to supplement addressee identification in tragedies using Large Language Models (LLMs). Unlike conventional Social Network Analysis (SNA) approaches, which often diminish dialogue dynamics by relying on co-occurrence or adjacency heuristics, our LLM-based method accurately records directed speech acts, joint addresses, and listener interactions. In a preliminary evaluation of an annotated multilingual dataset of 14 scenes from nine plays in four languages, our top-performing LLM (i.e., Llama3.3-70B) achieved an F1-score of 88.75% (P = 94.81%, R = 84.72%), an exact match of 77.31%, and an 86.97% partial match with human annotations, where partial match indicates any overlap between predicted and annotated receiver lists. Through automatic extraction of speaker–addressee relations, our method provides preliminary evidence for the potential scalability of SNA for literary analyses, as well as insights into power relations, influence, and isolation of characters in tragedies, which we further visualize by rendering social network graphs. Full article
Show Figures

Figure 1

18 pages, 640 KB  
Article
Fine-Tuning Methods and Dataset Structures for Multilingual Neural Machine Translation: A Kazakh–English–Russian Case Study in the IT Domain
by Zhanibek Kozhirbayev and Zhandos Yessenbayev
Electronics 2025, 14(15), 3126; https://doi.org/10.3390/electronics14153126 - 6 Aug 2025
Viewed by 769
Abstract
This study explores fine-tuning methods and dataset structures for multilingual neural machine translation using the No Language Left Behind model, with a case study on Kazakh, English, and Russian. We compare single-stage and two-stage fine-tuning approaches, as well as triplet versus non-triplet dataset [...] Read more.
This study explores fine-tuning methods and dataset structures for multilingual neural machine translation using the No Language Left Behind model, with a case study on Kazakh, English, and Russian. We compare single-stage and two-stage fine-tuning approaches, as well as triplet versus non-triplet dataset configurations, to improve translation quality. A high-quality, 50,000-triplet dataset in information technology domain, manually translated and expert-validated, serves as the in-domain benchmark, complemented by out-of-domain corpora like KazParC. Evaluations using BLEU, chrF, METEOR, and TER metrics reveal that single-stage fine-tuning excels for low-resource pairs (e.g., 0.48 BLEU, 0.77 chrF for Kazakh → Russian), while two-stage fine-tuning benefits high-resource pairs (Russian → English). Triplet datasets improve cross-linguistic consistency compared with non-triplet structures. Our reproducible framework offers practical guidance for adapting neural machine translation to technical domains and low-resource languages. Full article
Show Figures

Figure 1

34 pages, 2646 KB  
Article
Strengths and Weaknesses of LLM-Based and Rule-Based NLP Technologies and Their Potential Synergies
by Nikitas Ν. Karanikolas, Eirini Manga, Nikoletta Samaridi, Vaios Stergiopoulos, Eleni Tousidou and Michael Vassilakopoulos
Electronics 2025, 14(15), 3064; https://doi.org/10.3390/electronics14153064 - 31 Jul 2025
Viewed by 1839
Abstract
Large Language Models (LLMs) have been the cutting-edge technology in natural language processing (NLP) in recent years, making machine-generated text indistinguishable from human-generated text. On the other hand, “rule-based” Natural Language Generation (NLG) and Natural Language Understanding (NLU) algorithms were developed in earlier [...] Read more.
Large Language Models (LLMs) have been the cutting-edge technology in natural language processing (NLP) in recent years, making machine-generated text indistinguishable from human-generated text. On the other hand, “rule-based” Natural Language Generation (NLG) and Natural Language Understanding (NLU) algorithms were developed in earlier years, and they have performed well in certain areas of Natural Language Processing (NLP). Today, an arduous task that arises is how to estimate the quality of the produced text. This process depends on the aspects of text that you need to assess, varying from correct grammar and syntax to more intriguing aspects such as coherence and semantical fluency. Although the performance of LLMs is high, the challenge is whether LLMs can cooperate with rule-based NLG/NLU technology by leveraging their assets to overcome LLMs’ weak points. This paper presents the basics of these two families of technologies and the applications, strengths, and weaknesses of each approach, analyzes the different ways of evaluating a machine-generated text, and, lastly, focuses on a first-level approach of possible combinations of these two approaches to enhance performance in specific tasks. Full article
Show Figures

Figure 1

20 pages, 918 KB  
Article
Moral Judgment with a Large Language Model-Based Agent
by Shuchu Xiong, Haozhan Gu, Wei Liang and Lu Yin
Electronics 2025, 14(13), 2580; https://doi.org/10.3390/electronics14132580 - 26 Jun 2025
Viewed by 1015
Abstract
The ethical reasoning capability of large language models (LLMs) directly impacts their societal applicability, and enhancing this capacity is critical for developing trustworthy and secure artificial intelligence (AI) systems. The existing moral judgment methods based on LLMs rely on a single cognitive theory [...] Read more.
The ethical reasoning capability of large language models (LLMs) directly impacts their societal applicability, and enhancing this capacity is critical for developing trustworthy and secure artificial intelligence (AI) systems. The existing moral judgment methods based on LLMs rely on a single cognitive theory and lack an information aggregation and transmission mechanism, which affects the accuracy and stability of moral judgment. In this paper, we propose MoralAgent, an agentic approach that utilizes LLMs for moral judgment. First, the moral judgment process is planned based on various moral judgment theories. Second, the four dynamic prompt templates and the memory module are designed, and the moral principle is constructed to assist the analysis. Finally, the memory module is coordinated with the dynamic prompt template to optimize data transmission efficiency. This method significantly outperforms three types of traditional methods on the MoralExceptQA dataset. Compared to the two existing categories of methods based on LLMs, the F1 score of the proposed method is at least 4.13% higher, with slightly lower variance. Extensive experiments and evaluation metrics demonstrate the effectiveness of the proposed method, and sample analysis shows how the judgment process works to ensure that the results are reliable. Full article
Show Figures

Figure 1

13 pages, 1347 KB  
Article
Enhancing Policy Generation with GraphRAG and YouTube Data: A Logistics Case Study
by Hisatoshi Naganawa and Enna Hirata
Electronics 2025, 14(7), 1241; https://doi.org/10.3390/electronics14071241 - 21 Mar 2025
Cited by 3 | Viewed by 2089
Abstract
Graph-based retrieval-augmented generation (GraphRAG) represents an innovative advancement in natural language processing, leveraging the power of large language models (LLMs) for complex tasks such as policy generation. This research presents a GraphRAG model trained on YouTube data containing keywords related to logistics issues [...] Read more.
Graph-based retrieval-augmented generation (GraphRAG) represents an innovative advancement in natural language processing, leveraging the power of large language models (LLMs) for complex tasks such as policy generation. This research presents a GraphRAG model trained on YouTube data containing keywords related to logistics issues to generate policy proposals addressing these challenges. The collected data include both video subtitles and user comments, which are used to fine-tune the GraphRAG model. To evaluate the effectiveness of this approach, the performance of the proposed model is compared to a standard generative pre-trained transformer (GPT) model. The results show that the GraphRAG model outperforms the GPT model in most prompts, highlighting its potential to generate more accurate and contextually relevant policy recommendations. This study not only contributes to the evolving field of LLM-based natural language processing (NLP) applications but also explores new methods for improving model efficiency and scalability in real-world domains like logistics policy making. Full article
Show Figures

Figure 1

Back to TopTop