arXiv Artificial Intelligence

Reinforcement Learning over Predictive Distributions for LLM Regression

2 hours ago 07.10.2026 07:00 👁 2 views
Reinforcement Learning over Predictive Distributions for LLM Regression

Quick summary

arXiv:2605.20740v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have emerged as flexible regressors capable of predicting real-valued quantities from heterogeneous inputs. Yet most LLM regression objectives optimize predictions independently, often yielding poor calibration. We introduce Distribution-Aware Reward (DAR), an on-policy reinforcement learning objective that instead jointly evaluates the empirical predictive distribution formed by multiple predictions for the same input. To translate this distribution-level objective into rollout-level rewards, we assign each

Key takeaways

  • arXiv:2605.20740v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have emerged as flexible regressors capable of predicting real-valued quantities from heterogeneous inputs.
  • Yet most LLM regression objectives optimize predictions independently, often yielding poor calibration.
  • We introduce Distribution-Aware Reward (DAR), an on-policy reinforcement learning objective that instead jointly evaluates the empirical predictive distribution formed by multiple predictions for the same input.

Why it matters

The significance is not only the legal text but how it changes product design. Decisions around “Reinforcement Learning over Predictive Distributions for LLM Regression” may reshape data collection, model training, output accountability and market access.

Kaynak sitede devamını oku: arXiv Artificial Intelligence ↗