Towards trustworthy AI: An analysis of the relationship between explainability and trust in AI systems
Bibliographic record
Abstract
As artificial intelligence (AI) becomes increasingly integral to our lives, ensuring these systems are trustworthy and transparent is paramount. The concept of explainability has emerged as a crucial element in fostering trust within AI systems. Nevertheless, the dynamics between explainability and trust in AI are intricate and not fully comprehended. This paper delves into the nexus between explainability and trust in AI, offering perspectives on crafting AI systems that users can rely on. Through an examination of existing literature, we investigate how transparency, accountability, and human oversight influence trust in AI systems and assess how various explainability approaches contribute to trust enhancement. Utilizing a set of experiments, our research examines how different explanatory models impact users' trust in AI systems, revealing that the nature and quality of explanations have a significant influence on trust levels. Additionally, we scrutinize the balance between explainability and accuracy in AI systems, discussing its implications for the development of reliable AI. This study underscores the critical role of explainability in engendering trust in AI systems, providing guidance on the development of AI systems that are both transparent and trustworthy, thereby fostering confidence among users.
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.
How this classification was reachedexpand
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 | 0.017 | 0.008 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.001 | 0.005 |
| Scholarly communication | 0.001 | 0.001 |
| 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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".