cs.CLApr 14, 2025

Reinforcement Learning with Reference-Based Rewards for Language Model Reasoning and Alignment

Authors: Shuai Zhao, Yunqiu Xu, Linchao Zhu, Ling Chen, Yi Yang

Organizations: University of Technology Sydney · ReLER Lab, CCAI, Zhejiang University

Abstract

Reinforcement learning (RL) powers two major lines of large language model (LLM) post-training: reasoning, which elicits deliberate, verifiable problem solving, and alignment, which steers models toward helpful, harmless, and honest behavior. Both hinge on reward design. Reasoning relies on rule-based verification of final answers, whose binary feedback is blind to intermediate derivations, whereas process reward models (PRMs) require step-level annotations too costly to scale. Alignment depends on reward models (RMs) trained on binary preference pairs, making both data collection and model training resource-intensive. We propose RL2R, reinforcement learning with reference-based rewards, as a unified and inexpensive alternative. Using pre-existing or distilled references, RL2R measures semantic similarity with lightweight metrics such as BERTScore between a sampled generation and a reference answer or solution. Similarity preserves ordinal quality signals that binary feedback discards: responses closer to the reference earn higher rewards, and sound derivations receive credit even when the final conclusion is wrong. For mathematical reasoning, augmenting rule-based verification with answer- and step-level similarity provides low-cost process supervision and outperforms answer-only verification. For alignment, a critic-free REINFORCE-style instantiation covers general preference, safety, and confidence tasks on par with RM-based methods. Reference-based rewards thus offer a cost-effective, versatile reward source spanning reasoning and alignment.

Figures & tables

Appendix figures & tables8 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Gradients Know What Outcomes Don't: Unlocking Reinforcement Learning for LLM Reasoning with Gradient-Aligned Rewards

    Sep 3, 2026Leqi Zheng, Jinbo Su, Fang Niu +8Numerical Reasoning in Language ModelsReward Shaping

  2. Reward Modeling for Reinforcement Learning-Based LLM Reasoning: Design, Challenges, and Evaluation

    Feb 10, 2026Pei-Chi Pan, Yingbin Liang, Sen LinReward ModelingReward Hacking

  3. Learning to Reason from Reference Samples Alone: Reinforced Adversarial Learning for Modern LLM Post-Training

    Oct 28, 2026Albert Bou, Javier Valdes-Aleman, Jon M. Laurent +4RL for Language Model ReasoningLLM Post-Training