The paper argues that misalignment is inevitable because full AI-human alignment is undecidable for Turing-complete agents, and presents an LLM debate experiment showing open models are more diverse and influenceable.
Assessing the alignment of large language models with 51 human values for mental health integration: Cross-sectional study using schwartz’s theory of basic values,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Neurodivergent Influenceability as a Contingent Solution to the AI Alignment Problem
The paper argues that misalignment is inevitable because full AI-human alignment is undecidable for Turing-complete agents, and presents an LLM debate experiment showing open models are more diverse and influenceable.