从求解到验证：面向大语言模型鲁棒推理的统一目标
From Solving to Verifying: A Unified Objective for Robust Reasoning in LLMs
AI总结：
针对大语言模型自验证能力不足的问题，提出GRPO-Verif算法，通过统一损失函数联合优化求解生成与自验证，在保持推理性能的同时提升自验证能力。
摘要：
大语言模型（LLMs）的推理能力已通过强化学习（RL）得到显著提升，但LLMs仍难以稳定验证自身的推理轨迹，这引出了如何增强LLMs自验证能力、以及该能力能否进一步提升推理性能的研究问题。本研究提出GRPO-Verif算法，在统一损失函数内联合优化解生成与自验证过程，通过可调超参数控制验证信号权重。实验结果表明，该方法在保持可比推理性能的同时，增强了模型的自验证能力。
英文摘要：
The reasoning capabilities of large language models (LLMs) have been significantly improved through reinforcement learning (RL). Nevertheless, LLMs still struggle to consistently verify their own reasoning traces. This raises the research question of how to enhance the self-verification ability of LLMs and whether such an ability can further improve reasoning performance. In this work, we propose GRPO-Verif, an algorithm that jointly optimizes solution generation and self-verification within a unified loss function, with an adjustable hyperparameter controlling the weight of the verification signal. Experimental results demonstrate that our method enhances self-verification capability while maintaining comparable performance in reasoning.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
