Knowledge Tree
Relations (1)
related 0.60 — strongly supporting 6 facts
Artificial intelligence is intrinsically linked to explainability as a core technical and ethical challenge, as evidenced by academic research [1], [2] and industry discourse [3], [4]. Furthermore, explainability is recognized as a critical priority for the future development and safety of AI systems [5], [6].
Facts (6)
Sources
Understanding LLM Understanding skywritingspress.ca 1 fact
referenceJocelyn Maclure authored the paper 'AI, explainability and public reason: The argument from the limitations of the human mind', published in Minds and Machines in 2021.
Building Trustworthy NeuroSymbolic AI Systems - arXiv arxiv.org 1 fact
claimGroundedness serves as the foundation for both explainability and safety in AI systems, as a lack of grounding in provided instructions can lead to unintended consequences.
Neuro-Symbolic AI: Explainability, Challenges, and Future Trends arxiv.org 1 fact
referenceDavid A. Broniatowski and colleagues authored a 2021 technical report for NIST titled 'Psychological foundations of explainability and interpretability in artificial intelligence'.
Medical Hallucination in Foundation Models and Their ... medrxiv.org 1 fact
claimSurvey respondents prioritized enhancing accuracy (12 mentions), explainability (10), ethical considerations including bias reduction and privacy (8), integration with existing tools (7), and improving speed and efficiency (3) as future priorities for AI improvement.
Neural-Symbolic AI: The Next Breakthrough in Reliable and ... hu.ac.ae 1 fact
claimArtificial intelligence has faced persistent challenges regarding transparency and explainability despite significant improvements in the field over the last decade.
Call for Papers: Special Session on KR and Machine Learning kr.org 1 fact
claimThe success of Machine Learning systems has highlighted issues like explainability, bias, and fairness, which encourages the integration of symbolic or interpretable representations into AI systems.