A Systematic Literature Review on AI Safety: Identifying Trends, Challenges, and Future Directions
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Artificial intelligence (AI) is revolutionizing many aspects of our lives, except it raises fundamental safety and ethical issues. In this survey paper, we review the current state of research on safe and trustworthy AI. This work provides a structured and systematic overview of AI safety. In which, we emphasize the significance of designing AI systems with safety focus, encompassing elements from data management, model development, and deployment. We underscore the need for AI systems to align with human values and operate within mounted ethical frameworks. In addition, we notice the need for a complete safety framework that courses the development and implementation of AI systems, ensuring they do not inadvertently cause damage to humans. Our results show that AI safety is associated with model learning techniques, verification and validation methods, failure modes, and managing AI autonomy. As discussed in the literature, the main concerns include explainability, interpretability, robustness, reliability, fairness, bias, and adversarial attacks.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it