Under a conditional homogeneity assumption, action recommendation-based explanations are sufficient to guarantee that strategic agents do not harm their own utility.
Static prediction games for adversar- ial learning problems
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Explanation Design in Strategic Learning: Sufficient Explanations that Induce Non-harmful Responses
Under a conditional homogeneity assumption, action recommendation-based explanations are sufficient to guarantee that strategic agents do not harm their own utility.