Unverified50% confidenceFactExact time
当恢复内部表征后，模型在涵盖宗教虔诚度、道德价值观、希望感和主观幸福感的标准化社会学问卷上的回答变得显著更接近人类
1
Sources
50%
Confidence
Long-term
Relevance
8/5/2026
First Seen
Sources
Related Claims
UnverifiedAnthropic在模型对齐研究中将诚实性（Honesty）列为核心价值观64% similarUnverified对偶像的祛魅并非负面事件，而是心理成熟度提升的重要标志，意味着个体将外部投射的理想收回并整合为自我需求60% similarUnverified心理学中的信念固着效应表明，即便谬误被明确纠正，人们仍倾向于保留最初印象54% similarUnverifiedFor tasks involving moral and value judgments, an increasing number of researchers advocate adopting a 'disagreement-aware' modeling approach, preserving annotator disagreement information rather than simply taking a majority vote.54% similarUnverifiedTop-tier models have approached the level of human judges on many evaluation tasks, but exhibit biases such as a tendency to give higher scores to longer responses54% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/690528API
curl https://kongchang.com/api/v1/knowledge/claims/690528MCP
get_claim(id=690528)