RLHF should decompose annotations into dimensions each matched to one of three models—extension, evidence, or authority—instead of applying a single unified pipeline.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CY 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
LLMs generate lower-quality STEM explanations for marginalized student profiles in Indian and American contexts, with intersectional compounding producing gaps of up to 2.55 grade levels.
citing papers explorer
-
Three Models of RLHF Annotation: Extension, Evidence, and Authority
RLHF should decompose annotations into dimensions each matched to one of three models—extension, evidence, or authority—instead of applying a single unified pipeline.
-
Compounding Disadvantage: Auditing Intersectional Bias in LLM-Generated Explanations Across Indian and American STEM Education
LLMs generate lower-quality STEM explanations for marginalized student profiles in Indian and American contexts, with intersectional compounding producing gaps of up to 2.55 grade levels.