Causal and Structured Representations for Trustworthy and Interpretable AI

A special issue of Electronics (ISSN 2079-9292). This special issue belongs to the section "Artificial Intelligence".

Deadline for manuscript submissions: 15 October 2026 | Viewed by 538

Editor


E-Mail Website
Guest Editor
Philosophy Department, Carnegie Mellon University, Pittsburgh, PA, USA
Interests: causality; representation learning; computer vision

Special Issue Information

Dear Colleagues,

Despite impressive success, many AI systems remain opaque, fragile and difficult to trust, especially in high-stakes and safety-critical applications. It motivates growing interest in AI approaches that go beyond black-box prediction and provide transparent, robust and reliable decision-making mechanisms.

Causality and structured representations offer a principled pathway toward trustworthy and interpretable AI. By modeling causal relationships, such representations enable deeper understanding, improved generalization, controllable modification and meaningful internal explanations. They also facilitate fairness analysis, accountability and effective human–AI interaction.

This Special Issue aims to bring together recent advances in causal modeling, structured representations and their integration with modern machine-learning and deep-learning systems. By combining theoretical developments with practical applications, the Special Issue seeks to present a coherent and focused collection of contributions that advance trustworthy and interpretable AI, while remaining sufficiently broad to attract a diverse set of high-quality submissions.

In this Special Issue, original research articles and review papers are welcome. Research areas may include, but are not limited to, the following:

Representation learning;

Causal discovery and causal inference;

Structured, relational and symbolic models;

Interpretable and explainable AI;

Reasoning;

Robustness, generalization, fairness and accountability in AI systems;

Human-centered and human-in-the-loop AI;

Applications in healthcare, scientific discovery, AI-empowered education, robotics, autonomous systems and other safety-critical or socially impactful domains.

We look forward to receiving your contributions.

Dr. Guangyi Chen
Guest Editor

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-anonymized 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

  • causality
  • representation learning
  • structured models
  • explainable AI
  • reasoning
  • generalization
  • fairness
  • AI-empowered applications

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 (1 paper)

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

Research

16 pages, 10831 KB  
Article
The Impact of Large Language Models on Content Quality in Social Media
by Zeinab Shahbazi and Magnus Johnsson
Electronics 2026, 15(13), 2820; https://doi.org/10.3390/electronics15132820 - 26 Jun 2026
Viewed by 187
Abstract
The increasing availability of large language models (LLMs) is transforming how users create and share content on social media platforms. Beyond enabling text generation, LLMs introduce a new paradigm in which content is deliberately optimized for engagement through algorithmically suggested phrasing, structure, and [...] Read more.
The increasing availability of large language models (LLMs) is transforming how users create and share content on social media platforms. Beyond enabling text generation, LLMs introduce a new paradigm in which content is deliberately optimized for engagement through algorithmically suggested phrasing, structure, and tone. This paper investigates the emerging shift from authentic self-expression toward engagement-driven optimization in LLM-assisted social media use. It examines whether and how LLM-generated or LLM-assisted posts systematically outperform human-authored content in engagement metrics and at what cost to informational quality, diversity, and authenticity. Using a mixed-methods approach, controlled experiments with human participants are combined with large-scale analysis of social media posts to compare organic and LLM-optimized content. Differences in engagement outcomes (e.g., likes, shares, comments), linguistic features, and perceived credibility and informativeness are evaluated. The findings suggest that while LLM-assisted content consistently increases short-term engagement, it tends to reduce informational depth and perceived authenticity while exhibiting changes in stylistic characteristics associated with engagement-oriented optimization. This creates a potential feedback loop in which users increasingly rely on optimization strategies that privilege attention over substance. The findings suggest that widespread adoption of LLM-driven optimization could contribute to changes in the dynamics of the social media attention economy. Future research is needed to determine whether these effects emerge at scale and persist over longer periods of platform use. Implications are discussed for platform design, content moderation, and the future of human–AI co-creation in digital communication. Full article
Show Figures

Figure 1

Back to TopTop