Distribution-Aware Reward optimizes LLM regression by treating rollouts as empirical predictive distributions and rewarding marginal improvements in CRPS quality rather than point accuracy alone.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2verdicts
UNVERDICTED 2representative citing papers
LASER uses fine-tuned LLMs with scientific-notation output encoding and constrained decoding to regress resource and runtime targets from semi-structured workflow configurations, outperforming tabular baselines and experts on chip-design and GitHub Actions data.
citing papers explorer
-
Distribution-Aware Reward: Reinforcement Learning over Predictive Distributions for LLM Regression
Distribution-Aware Reward optimizes LLM regression by treating rollouts as empirical predictive distributions and rewarding marginal improvements in CRPS quality rather than point accuracy alone.
-
LASER: Language Model Regression for Semi-Structured Workflow Resource and Runtime Estimation
LASER uses fine-tuned LLMs with scientific-notation output encoding and constrained decoding to regress resource and runtime targets from semi-structured workflow configurations, outperforming tabular baselines and experts on chip-design and GitHub Actions data.