A technique identifies minimal convergence-divergence points in LLM transformer blocks and calibrates residual-stream directions to achieve targeted ethical-framework control at inference time.
In9th International Conference on Learning Representa- tions, ICLR 2021, Virtual Event, Austria, May 3-7
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
DVMap extracts high-consensus demographic groups from survey data and applies structured CoT plus GRPO to align LLMs with pluralistic values, reporting 48.6% accuracy on cross-demographic generalization tests.
citing papers explorer
-
Where Paths Split: Localized, Calibrated Control of Moral Reasoning in Large Language Models
A technique identifies minimal convergence-divergence points in LLM transformer blocks and calibrates residual-stream directions to achieve targeted ethical-framework control at inference time.
-
DVMap: Fine-Grained Pluralistic Value Alignment via High-Consensus Demographic-Value Mapping
DVMap extracts high-consensus demographic groups from survey data and applies structured CoT plus GRPO to align LLMs with pluralistic values, reporting 48.6% accuracy on cross-demographic generalization tests.