Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

RLPR: Extrapolating RLVR to General Domains without Verifiers

About

Reinforcement Learning with Verifiable Rewards (RLVR) demonstrates promising potential in advancing the reasoning capabilities of LLMs. However, its success remains largely confined to mathematical and code domains. This primary limitation stems from the heavy reliance on domain-specific verifiers, which results in prohibitive complexity and limited scalability. To address the challenge, our key observation is that LLM's intrinsic probability of generating a correct free-form answer directly indicates its own evaluation of the reasoning reward (i.e., how well the reasoning process leads to the correct answer). Building on this insight, we propose RLPR, a simple verifier-free framework that extrapolates RLVR to broader general domains. RLPR uses the LLM's own token probability scores for reference answers as the reward signal and maximizes the expected reward during training. We find that addressing the high variance of this noisy probability reward is crucial to make it work, and propose prob-to-reward and stabilizing methods to ensure a precise and stable reward from LLM intrinsic probabilities. Comprehensive experiments in four general-domain benchmarks and three mathematical benchmarks show that RLPR consistently improves reasoning capabilities in both areas for Gemma, Llama, and Qwen based models. Notably, RLPR outperforms concurrent VeriFree by 7.6 points on TheoremQA and 7.5 points on Minerva, and even surpasses strong verifier-model-dependent approaches General-Reasoner by 1.6 average points across seven benchmarks.

Tianyu Yu, Bo Ji, Shouli Wang, Shu Yao, Zefan Wang, Ganqu Cui, Lifan Yuan, Ning Ding, Yuan Yao, Zhiyuan Liu, Maosong Sun, Tat-Seng Chua• 2025

Related benchmarks

TaskDatasetResultRank
Instruction FollowingIFEval
Accuracy (0-100)74.6
292
Instruction FollowingAlpacaEval 2.0
LC Win Rate30.8
281
Mathematical ReasoningAIME 2024
Accuracy24.5
251
General KnowledgeMMLU
MMLU General Knowledge Accuracy68.7
170
Mathematical Problem SolvingMATH
Accuracy52.7
166
Mathematical ReasoningAMC
Accuracy53
151
Mathematical ReasoningAMC
Pass@124.92
112
Mathematical ReasoningAIME 2025
Pass@10.96
96
Mathematical ReasoningAIME 2024
Pass@110
86
CodeHumanEval
HumanEval Accuracy72.3
50
Showing 10 of 43 rows

Other info

Follow for update