ArticleArtificial intelligence review2025
Safeguarding large language models: a survey.
Article in Artificial intelligence review, 2025. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 14 papers.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
14 citing papers in PubMed.
- Article
- Gradient-guided layerwise adaptive noise injection for pre-trained language model fine-tuning.Scientific reports · 2026Article
- Can Artificial Intelligence Chatbots Plan Therapeutic Ketogenic Diets for Children With Epilepsy?Journal of human nutrition and dietetics : the official journal of the British Dietetic Association · 2026Article
- Artificial Intelligence Literacy in Intensive Care: From Algorithmic Fluency to Clinical Accountability.Indian journal of critical care medicine : peer-reviewed, official publication of Indian Society of Critical Care Medicine · 2026Article
- Article
- Beyond Simulations: What 20,000 Real Conversations Reveal About Mental Health AI Safety.Research square · 2026Article
- Recent advances in defending the privacy attacks of large language models for healthcare applications: a concise review.Frontiers in artificial intelligence · 2026Review
- Dual-use artificial intelligence and biology: upstream risk-benefit reviews.Frontiers in microbiology · 2026Article
- Knowledge distillation and dataset distillation of large language models: emerging trends, challenges, and future directions.Artificial intelligence review · 2026Article
- Vulnerability of Large Language Models to Prompt Injection When Providing Medical Advice.JAMA network open · 2025Article
- A Prompt Engineering Framework for Large Language Model-Based Mental Health Chatbots: Conceptual Framework.JMIR mental health · 2025Article
- Conversational AI in Pediatric Mental Health: A Narrative Review.Children (Basel, Switzerland) · 2025Review
- Without safeguards, AI-Biology integration risks accelerating future pandemics.Frontiers in microbiology · 2025Article
- Agentic LLM-based robotic systems for real-world applications: a review on their agenticness and ethics.Frontiers in robotics and AI · 2025Review
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
12 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
In the burgeoning field of Large Language Models (LLMs), developing a robust safety mechanism, colloquially known as "safeguards" or "guardrails", has become imperative to ensure the ethical use of LLMs within prescribed boundaries. This article provides a systematic literature review on the current status of this critical mechanism. It discusses its major challenges and how it can be enhanced into a comprehensive mechanism dealing with ethical issues in various contexts. First, the paper elucidates the current landscape of safeguarding mechanisms that major LLM service providers and the open-source community employ. This is followed by the techniques to evaluate, analyze, and enhance some (un)desirable properties that a guardrail might want to enforce, such as hallucinations, fairness, privacy, and so on. Based on them, we review techniques to circumvent these controls (i.e., attacks), to defend the attacks, and to reinforce the guardrails. While the techniques mentioned above represent the current status and the active research trends, we also discuss several challenges that cannot be easily dealt with by the methods and present our vision on how to implement a comprehensive guardrail through the full consideration of multi-disciplinary approach, neural-symbolic method, and systems development lifecycle.
Indexed as
Identifiers
What Socratic holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the Socratic graph.