Evaluator-specific demonstrations with retrospective reasoning improve LLM simulation of individual preference judges by up to 9.9 points over a non-personalized base judge, while interface telemetry often degrades accuracy.
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers) , pages=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3roles
background 1polarities
support 1representative citing papers
COALA applies convex optimization reformulations of neural networks to direct preference optimization, claiming single-GPU training with ~18% of DPO's TFLOPs and competitive performance on multiple datasets and models up to 8B parameters.
SelectiveRM applies optimal transport with a joint consistency discrepancy and partial mass relaxation to produce reward models that optimize a tighter upper bound on clean risk while autonomously dropping noisy preference samples.
citing papers explorer
-
Convex Optimization for Alignment and Preference Learning on a Single GPU
COALA applies convex optimization reformulations of neural networks to direct preference optimization, claiming single-GPU training with ~18% of DPO's TFLOPs and competitive performance on multiple datasets and models up to 8B parameters.