Trustworthy Large Language Models: Advancing Reliability, Safety, Fairness, and Transparency

Dear Colleagues,

The widespread integration of Large Language Models (LLMs) into critical applications—from healthcare and education to finance and law—has made trustworthiness a central concern for the AI community. Despite their impressive fluency and versatility, LLMs frequently exhibit hallucinations, amplify societal biases, leak private information, and remain susceptible to adversarial manipulation. These shortcomings not only degrade user experience but also pose tangible risks, including misinformation propagation, unfair decision-making, and security breaches. Consequently, the research frontier has shifted from merely scaling models to ensuring that LLMs are reliable, safe, fair, transparent, and aligned with human values.

This Special Issue solicits original research and comprehensive review articles that address the multifaceted challenges of building trustworthy LLMs. We invite contributions that advance the state-of-the art in detecting and mitigating hallucinations, measuring and reducing bias, strengthening robustness against prompt injection and jailbreaking, preserving privacy in model training and inference, enhancing explainability and interpretability, developing rigorous evaluation benchmarks, and aligning model outputs with ethical and legal norms. We also encourage interdisciplinary perspectives that examine societal impact, user trust dynamics, and regulatory frameworks. By consolidating pioneering work in these areas, this Special Issue aims to shape a research agenda for the next generation of LLMs that are not only powerful but also demonstrably trustworthy.

Prof. Dr. Yonghui Xu
Prof. Dr. Jun Lin
Prof. Dr. Jun Zhang
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-anonymized peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. AI 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.