Diversity or Precision? A Deep Dive into Next Token Prediction

TL;DR

This paper explores how adjusting the pre-trained token distribution in language models influences reinforcement learning effectiveness, proposing a reward-shaping strategy that balances diversity and precision to improve reasoning capabilities.

Contribution

It introduces a generalized pre-training objective with reward shaping and rank-aware mechanisms, enhancing exploration space for RL in language models.

Findings

Imposing a precision-oriented prior improves RL exploration.

Reward shaping balances diversity and precision effectively.

Reshaping token distribution enhances reasoning performance.

Abstract

Recent advancements have shown that reinforcement learning (RL) can substantially improve the reasoning abilities of large language models (LLMs). The effectiveness of such RL training, however, depends critically on the exploration space defined by the pre-trained model's token-output distribution. In this paper, we revisit the standard cross-entropy loss, interpreting it as a specific instance of policy gradient optimization applied within a single-step episode. To systematically study how the pre-trained distribution shapes the exploration potential for subsequent RL, we propose a generalized pre-training objective that adapts on-policy RL principles to supervised learning. By framing next-token prediction as a stochastic decision process, we introduce a reward-shaping strategy that explicitly balances diversity and precision. Our method employs a positive reward scaling factor to control probability concentration on ground-truth tokens and a rank-aware mechanism that treats high-ranking and low-ranking negative tokens asymmetrically. This allows us to reshape the pre-trained token-output distribution and investigate how to provide a more favorable exploration space for RL, ultimately enhancing end-to-end reasoning performance. Contrary to the intuition that higher distribution entropy facilitates effective exploration, we find that imposing a precision-oriented prior yields a superior exploration space for RL.