Authors argue that value alignment requires avoiding derivation of ought from is and suggest quantified modal logic to integrate ethical principles with facts for more human-like ethical reasoning in AI.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Grounding Value Alignment with Ethical Principles
Authors argue that value alignment requires avoiding derivation of ought from is and suggest quantified modal logic to integrate ethical principles with facts for more human-like ethical reasoning in AI.