A Method for Learning Value Systems in Generative AI
Value-aware AI systems require explicit computational representations of human values (groundings) and their aggregation into value systems in order to align their decisions with ours. As such representations are difficult to elicit, value learning seeks to infer them by observing human behaviour. This work addresses the lack of grounded value learning methods in generative AI: existing approaches typically replicate human preferences without awareness of the multidimensional structure of value alignment, or lack principled value system elicitation methods. To address these gaps, we adapt a pr
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 47%General Intuition’s $2.3B bet that video games can train AI agents for the real world →
- PossiblePossibly related (embedding) · 46%Northwind AI →
- FuzzySimilar title/name (fuzzy) · 84%GoogleCloudPlatform/generative-ai →
“Fuzzy title match (0.92): “A Method for Learning Value Systems in Generative AI” ≈ “GoogleCloudPlatform/generative-ai””
- FuzzySimilar title/name (fuzzy) · 59%aymericdamien/TopDeepLearning →
“Fuzzy title match (0.73): “A Method for Learning Value Systems in Generative AI” ≈ “aymericdamien/TopDeepLearning””
- LinkedLinked via arxiv author · 85%Andrés Holgado-Sánchez →
“A Method for Learning Value Systems in Generative AI”
- LinkedLinked via arxiv author · 85%Holger Billhardt →
“A Method for Learning Value Systems in Generative AI”
- LinkedLinked via arxiv author · 85%Sascha Ossowski →
“A Method for Learning Value Systems in Generative AI”