LLM praise and critique of user-stated intentions are driven more by source trustworthiness than ideology, align broadly with human moral scores, and show no country-of-origin bias.
In Companion of the 2021 ACM/IEEE International Conference on Human-Robot Interaction, HRI ’21 Companion, 10–18
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CY 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
What does AI consider praiseworthy?
LLM praise and critique of user-stated intentions are driven more by source trustworthiness than ideology, align broadly with human moral scores, and show no country-of-origin bias.