Beyond Token-level Supervision: Unlocking the Potential of Decoding-based Regression via Reinforcement Learning

TL;DR

This paper introduces a reinforcement learning approach to decoding-based regression, improving the alignment between sequence generation and continuous numerical prediction, leading to better accuracy and efficiency.

Contribution

It proposes a novel RL framework for decoding-based regression, utilizing sequence-level rewards to enhance numerical coherence and outperform existing token-level methods.

Findings

RL improves sampling efficiency and predictive accuracy.

The method outperforms state-of-the-art token-level baselines.

Decoding-based regression becomes more robust and precise.

Abstract

Decoding-based regression, which reformulates regression as a sequence generation task, has emerged as a promising paradigm of applying large language models for numerical prediction. However, its progress is hindered by the misalignment between discrete token-level objectives (e.g., cross-entropy) and continuous numerical values. Existing approaches relying on token-level constraints often fail to capture the global magnitude of the target value, limiting their precision and generalization. In this paper, we propose to unlock the potential of decoding-based regression via Reinforcement Learning (RL). We formulate the generation process as a Markov Decision Process, utilizing sequence-level rewards to enforce global numerical coherence. Extensive experiments on tabular regression and code metric regression demonstrate that our method (specifically with ReMax and GRPO) consistently outperforms both state-of-the-art token-level baselines and traditional regression heads, showing the superiority of introducing sequence-level signals. Our analysis further reveals that RL significantly enhances sampling efficiency and predictive precision, establishing decoding-based regression as a robust and accurate paradigm for general-purpose numerical prediction.