Deployment-relevant AI alignment cannot be inferred from model-level evaluations alone, as benchmark audits show missing interaction support and cross-model tests reveal model-dependent scaffold effects.
CURATe: Benchmarking personalised alignment of conversational AI assistants
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.AI 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Pluralistic AI alignment requires surfacing value conflicts via scoping, signalling, and repair rather than preference aggregation alone, as evidenced by low repair quality on contested prompts in tested frontier models.
citing papers explorer
-
Deployment-Relevant Alignment Cannot Be Inferred from Model-Level Evaluation Alone
Deployment-relevant AI alignment cannot be inferred from model-level evaluations alone, as benchmark audits show missing interaction support and cross-model tests reveal model-dependent scaffold effects.
-
From Sycophantic Consensus to Pluralistic Repair: Why AI Alignment Must Surface Disagreement
Pluralistic AI alignment requires surfacing value conflicts via scoping, signalling, and repair rather than preference aggregation alone, as evidenced by low repair quality on contested prompts in tested frontier models.