Spurious Rewards: Rethinking Training Signals in RLVR

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Shao, Rulin, Li, Shuyue Stella, Xin, Rui, Geng, Scott, Wang, Yiping, Oh, Sewoong, Du, Simon Shaolei, Lambert, Nathan, Min, Sewon, Krishna, Ranjay, Tsvetkov, Yulia, Hajishirzi, Hannaneh, Koh, Pang Wei, Zettlemoyer, Luke
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866918354827083776
author Shao, Rulin
Li, Shuyue Stella
Xin, Rui
Geng, Scott
Wang, Yiping
Oh, Sewoong
Du, Simon Shaolei
Lambert, Nathan
Min, Sewon
Krishna, Ranjay
Tsvetkov, Yulia
Hajishirzi, Hannaneh
Koh, Pang Wei
Zettlemoyer, Luke
author_facet Shao, Rulin
Li, Shuyue Stella
Xin, Rui
Geng, Scott
Wang, Yiping
Oh, Sewoong
Du, Simon Shaolei
Lambert, Nathan
Min, Sewon
Krishna, Ranjay
Tsvetkov, Yulia
Hajishirzi, Hannaneh
Koh, Pang Wei
Zettlemoyer, Luke
contents We show that reinforcement learning with verifiable rewards (RLVR) can elicit strong mathematical reasoning in certain language models even with spurious rewards that have little, no, or even negative correlation with the correct answer. For example, RLVR training with GRPO improves MATH-500 performance for Qwen2.5-Math-7B by 21.4 percentage points using randomly assigned rewards, nearly matching the 29.1-point gain from ground-truth rewards. To explain this counterintuitive observation, we show that GRPO exhibits a clipping bias from the clip term, which can amplify high-prior behaviors learned during pretraining even without informative rewards. As a case study, we identify one such behavior in Qwen2.5-Math models, which we call code reasoning -- reasoning in code without actual code execution; code-reasoning frequency increases from 65 percent to over 90 percent with spurious rewards. However, the presence of such amplifiable behaviors is highly model-dependent. In practice, spurious rewards that are effective for Qwen models often fail to produce gains for other model families, such as Llama3 or OLMo2. Our results highlight the importance of validating RL methods across diverse models rather than relying on a single de facto choice: large gains can arise on Qwen models even from random rewards that do not reflect genuine capability improvements.
format Preprint
id arxiv_https___arxiv_org_abs_2506_10947
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Spurious Rewards: Rethinking Training Signals in RLVR
Shao, Rulin
Li, Shuyue Stella
Xin, Rui
Geng, Scott
Wang, Yiping
Oh, Sewoong
Du, Simon Shaolei
Lambert, Nathan
Min, Sewon
Krishna, Ranjay
Tsvetkov, Yulia
Hajishirzi, Hannaneh
Koh, Pang Wei
Zettlemoyer, Luke
Artificial Intelligence
Machine Learning
We show that reinforcement learning with verifiable rewards (RLVR) can elicit strong mathematical reasoning in certain language models even with spurious rewards that have little, no, or even negative correlation with the correct answer. For example, RLVR training with GRPO improves MATH-500 performance for Qwen2.5-Math-7B by 21.4 percentage points using randomly assigned rewards, nearly matching the 29.1-point gain from ground-truth rewards. To explain this counterintuitive observation, we show that GRPO exhibits a clipping bias from the clip term, which can amplify high-prior behaviors learned during pretraining even without informative rewards. As a case study, we identify one such behavior in Qwen2.5-Math models, which we call code reasoning -- reasoning in code without actual code execution; code-reasoning frequency increases from 65 percent to over 90 percent with spurious rewards. However, the presence of such amplifiable behaviors is highly model-dependent. In practice, spurious rewards that are effective for Qwen models often fail to produce gains for other model families, such as Llama3 or OLMo2. Our results highlight the importance of validating RL methods across diverse models rather than relying on a single de facto choice: large gains can arise on Qwen models even from random rewards that do not reflect genuine capability improvements.
title Spurious Rewards: Rethinking Training Signals in RLVR
topic Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2506.10947