Rubric embeddings from expert criteria mitigate label bias in models trained on historical evaluations, reducing group disparities while improving cohort quality on a master's program dataset.
Unsupervised elicitation of language models, 2025
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2verdicts
UNVERDICTED 2representative citing papers
Parallel inference rollouts aggregated into pseudo-references enable reference-free RL supervision that matches expert-annotated performance on health tasks while using 9x less test-time compute.
citing papers explorer
-
Mitigating Label Bias with Interpretable Rubric Embeddings
Rubric embeddings from expert criteria mitigate label bias in models trained on historical evaluations, reducing group disparities while improving cohort quality on a master's program dataset.
-
Compute as Teacher: Turning Inference Compute Into Reference-Free Supervision
Parallel inference rollouts aggregated into pseudo-references enable reference-free RL supervision that matches expert-annotated performance on health tasks while using 9x less test-time compute.