Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
9.9
6.0
Journals
MAKE
Special Issues
Using Large Language Models for Scientific Problem Solving and Engineering...
share announcement

Using Large Language Models for Scientific Problem Solving and Engineering Design

A special issue of Machine Learning and Knowledge Extraction (ISSN 2504-4990). This special issue belongs to the section "Learning".

Deadline for manuscript submissions: 31 December 2026 | Viewed by 10658

Special Issue Editors

Prof. Dr. Alex Doboli

E-Mail Website
Guest Editor
Department of Electrical and Computer Engineering, Stony Brook University, Stony Brook, NY 11794-2350, USA
Interests: electronic design automation; machine learning; design creativity; cyber-social systems
Special Issues, Collections and Topics in MDPI journals
Prof. Dr. K. Wendy Tang

E-Mail Website
Guest Editor
Department of Electrical and Compute Engineering, College of Engineering and Applied Sciences, Stony Brook University, Stony Brook, NY 11794-2350, USA
Interests: machine learning; graph theory applications
Prof. Dr. Simona Doboli

E-Mail Website
Guest Editor
Computer Science Department, De Matteis School of Engineering and Applied Sciences, Hofstra University, Hempstead, NY 11549, USA
Interests: deep learning; machine learning; hybrid symbolic reasoning, retrieval, and generative models

Special Issue Information

Dear Colleagues,

This Special Issue is dedicated to papers presenting overviews and state-of-the-art methods that use Large Language Models (LLMs) for scientific problem solving and engineering design. LLMs offer several intriguing, new capabilities, like content creation, summarization, question answering, translation, interfacing to human language, and so on. Still, problem solving and design automation also involve specific activities, which require devising more effective techniques for problem framing, solution partitioning, creating correct and optimized implementations (designs), addressing a broad set of constraints, incorporating human preferences, to name a few. We encourage interdisciplinary submissions that bridge machine learning, electronic design automation, design science, and cognitive science, but any work discussing using LLMs for problem solving and design is of interest.

Prof. Dr. Alex Doboli
Prof. Dr. K. Wendy Tang
Prof. Dr. Simona Doboli
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 250 words) can be sent to the Editorial Office for assessment.

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. Machine Learning and Knowledge Extraction is an international peer-reviewed open access monthly 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 1800 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

  • large language models
  • problem solving
  • automated engineering design
  • agents
  • prompting
  • reinforcement learning
  • retrieval-augmented generation
  • symbolic machine learning
  • knowledge representations

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 (5 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

23 pages, 844 KB  
Article
Soft-Prompted Semantic Normalization for Unsupervised Analysis of the Scientific Literature
by Ivan Malashin, Dmitry Martysyuk, Vadim Tynchenko, Andrei Gantimurov, Vladimir Nelyub and Aleksei Borodulin
Mach. Learn. Knowl. Extr. 2026, 8(3), 63; https://doi.org/10.3390/make8030063 - 5 Mar 2026
Cited by 1 | Viewed by 673
Abstract
Mapping thematic structure in large scientific corpora enables the systematic analysis of research trends and conceptual organization. This work presents an unsupervised framework that leverages large language models (LLMs) as fixed semantic inference operators guided by structured soft prompts. The framework transforms raw [...] Read more.
Mapping thematic structure in large scientific corpora enables the systematic analysis of research trends and conceptual organization. This work presents an unsupervised framework that leverages large language models (LLMs) as fixed semantic inference operators guided by structured soft prompts. The framework transforms raw abstracts into normalized semantic representations that reduce stylistic variability while retaining core conceptual content. These representations are embedded into a continuous vector space, where density-based clustering identifies latent research themes without predefining the number of topics. Cluster-level interpretation is performed using LLM-based semantic decoding to generate concise, human-readable descriptions of the discovered themes. Experiments on ICML and ACL 2025 abstracts demonstrate that the method produces coherent clusters reflecting problem formulations, methodological contributions, and empirical contexts. The findings indicate that prompt-driven semantic normalization combined with geometric analysis provides a scalable and model-agnostic approach for unsupervised thematic discovery across large scholarly corpora. Full article
(This article belongs to the Special Issue Using Large Language Models for Scientific Problem Solving and Engineering Design)
►▼ Show Figures

Graphical abstract

37 pages, 20040 KB  
Article
Towards LLM-Driven Cybersecurity in Autonomous Vehicles: A Big Data-Empowered Framework with Emerging Technologies
by Aristeidis Karras, Leonidas Theodorakopoulos, Christos Karras and Alexandra Theodoropoulou
Mach. Learn. Knowl. Extr. 2026, 8(2), 43; https://doi.org/10.3390/make8020043 - 11 Feb 2026
Viewed by 1465
Abstract
Modern Autonomous Vehicles generate large volumes of heterogeneous in-vehicle data, making cybersecurity a critical challenge as adversarial attacks become increasingly adaptive, stealthy, and multi-protocol. Traditional intrusion detection systems often fail under these conditions because of their limited contextual understanding, poor robustness to distribution [...] Read more.
Modern Autonomous Vehicles generate large volumes of heterogeneous in-vehicle data, making cybersecurity a critical challenge as adversarial attacks become increasingly adaptive, stealthy, and multi-protocol. Traditional intrusion detection systems often fail under these conditions because of their limited contextual understanding, poor robustness to distribution shifts, and insufficient regulatory transparency. This study introduces LLM-Guardian, a hierarchical intrusion detection framework with decision-making mechanisms that integrates Large Language Models (LLMs) with classical statistical detection theory, optimal transport drift analysis, graph neural networks, and formal uncertainty quantification. LLM-Guardian uses semantic anomaly scoring, conformal prediction for distribution-free confidence calibration, adaptive cumulative sum (CUSUM) sequential testing for low-latency detection, and topology-aware GNN reasoning designed to identify coordinated attacks across CAN, Ethernet, and V2X interfaces. In this work, the framework is empirically evaluated on four heterogeneous CAN-bus datasets, while the Ethernet and V2X components are instantiated at the architectural level and left as directions for future multi-protocol experimentation. Full article
(This article belongs to the Special Issue Using Large Language Models for Scientific Problem Solving and Engineering Design)
►▼ Show Figures

Graphical abstract

25 pages, 11437 KB  
Article
Enhancing the Extraction of GHG Emission-Reduction Targets from Sustainability Reports Using Vision Language Models
by Lars Wilhelmi, Christian Bruns and Matthias Schumann
Mach. Learn. Knowl. Extr. 2026, 8(2), 37; https://doi.org/10.3390/make8020037 - 5 Feb 2026
Viewed by 954
Abstract
This study investigates how Vision Language Models (VLMs) can be used and methodically configured to extract Environmental, Social, and Governance (ESG) metrics from corporate sustainability reports, addressing the limitations of existing text-only and manual ESG data-extraction approaches. Using the Design Science Research Methodology, [...] Read more.
This study investigates how Vision Language Models (VLMs) can be used and methodically configured to extract Environmental, Social, and Governance (ESG) metrics from corporate sustainability reports, addressing the limitations of existing text-only and manual ESG data-extraction approaches. Using the Design Science Research Methodology, we developed an extraction artifact comprising a curated page-level dataset containing greenhouse gas (GHG) emission-reduction targets, an automated evaluation pipeline, model and text-preprocessing comparisons, and iterative prompt and few-shot refinement. Pages from oil and gas sustainability reports were processed directly by VLMs to preserve visual–textual structure, enabling a controlled comparison of text, image, and combined input modalities, with extraction quality assessed at page and attribute level using F1-scores. Among tested models, Mistral Small 3.2 demonstrated the most stable performance and was used to evaluate image, text, and combined modalities. Combined text + image modality performed best (F1 = 0.82), particularly on complex page layouts. The findings demonstrate how to effectively integrate visual and textual cues for ESG metric extraction with VLMs, though challenges remain for visually dense layouts and avoiding inference-based hallucinations. Full article
(This article belongs to the Special Issue Using Large Language Models for Scientific Problem Solving and Engineering Design)
►▼ Show Figures

Graphical abstract

27 pages, 4789 KB  
Article
Assessing Interaction Quality in Human–AI Dialogue: An Integrative Review and Multi-Layer Framework for Conversational Agents
by Luca Marconi, Luca Longo and Federico Cabitza
Mach. Learn. Knowl. Extr. 2026, 8(2), 28; https://doi.org/10.3390/make8020028 - 26 Jan 2026
Cited by 1 | Viewed by 3982
Abstract
Conversational agents are transforming digital interactions across various domains, including healthcare, education, and customer service, thanks to advances in large language models (LLMs). As these systems become more autonomous and ubiquitous, understanding what constitutes high-quality interaction from a user perspective is increasingly critical. [...] Read more.
Conversational agents are transforming digital interactions across various domains, including healthcare, education, and customer service, thanks to advances in large language models (LLMs). As these systems become more autonomous and ubiquitous, understanding what constitutes high-quality interaction from a user perspective is increasingly critical. Despite growing empirical research, the field lacks a unified framework for defining, measuring, and designing user-perceived interaction quality in human–artificial intelligence (AI) dialogue. Here, we present an integrative review of 125 empirical studies published between 2017 and 2025, spanning text-, voice-, and LLM-powered systems. Our synthesis identifies three consistent layers of user judgment: a pragmatic core (usability, task effectiveness, and conversational competence), a social–affective layer (social presence, warmth, and synchronicity), and an accountability and inclusion layer (transparency, accessibility, and fairness). These insights are formalised into a four-layer interpretive framework—Capacity, Alignment, Levers, and Outcomes—operationalised via a Capacity × Alignment matrix that maps distinct success and failure regimes. It also identifies design levers such as anthropomorphism, role framing, and onboarding strategies. The framework consolidates constructs, positions inclusion and accountability as central to quality, and offers actionable guidance for evaluation and design. This research redefines interaction quality as a dialogic construct, shifting the focus from system performance to co-orchestrated, user-centred dialogue quality. Full article
(This article belongs to the Special Issue Using Large Language Models for Scientific Problem Solving and Engineering Design)
►▼ Show Figures

Graphical abstract

36 pages, 3276 KB  
Article
Robot Planning via LLM Proposals and Symbolic Verification
by Drejc Pesjak and Jure Žabkar
Mach. Learn. Knowl. Extr. 2026, 8(1), 22; https://doi.org/10.3390/make8010022 - 16 Jan 2026
Viewed by 2710
Abstract
Planning in robotics represents an ongoing research challenge, as it requires the integration of sensing, reasoning, and execution. Although large language models (LLMs) provide a high degree of flexibility in planning, they often introduce hallucinated goals and actions and consequently lack the formal [...] Read more.
Planning in robotics represents an ongoing research challenge, as it requires the integration of sensing, reasoning, and execution. Although large language models (LLMs) provide a high degree of flexibility in planning, they often introduce hallucinated goals and actions and consequently lack the formal reliability of deterministic methods. In this paper, we address this limitation by proposing a hybrid Sense–Plan–Code–Act (SPCA) framework that combines perception, LLM-based reasoning, and symbolic planning. Within the proposed approach, sensory information is first transformed into a symbolic description of the world in Planning Domain Definition Language (PDDL) using an LLM. A heuristic planner is then used to generate a valid plan, which is subsequently converted to code by a second LLM. The generated code is first validated syntactically through compilation and then semantically in simulation. When errors are detected, local corrections can be applied and the process is repeated as necessary. The proposed method is evaluated in the OpenAI Gym MiniGrid reinforcement learning environment and in a Gazebo simulation on a UR5 robotic arm using a curriculum of tasks with increasing complexity. The system successfully completes approximately 71–75% of tasks across environments with a relatively low number of simulation iterations. Full article
(This article belongs to the Special Issue Using Large Language Models for Scientific Problem Solving and Engineering Design)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-5
Back to TopTop