大型语言模型可通过关键条件验证实现自我纠正
Large Language Models Can Self-Correct with Key Condition Verification
AI总结:
本文提出ProCo框架,通过掩码关键条件构造验证问题,以迭代“先验证后纠正”的方式释放LLMs自我纠正能力,在多个推理任务上显著优于Self-Correct。
摘要:
内在自我纠正是一种指示大型语言模型(LLMs)在无外部反馈的情况下验证并纠正其回答的方法。遗憾的是,此前研究得出结论,LLMs尚不能对推理过程进行自我纠正。我们发现,一种简单而有效的验证方法能够释放LLMs的固有能力。该方法将问题中的关键条件进行掩码处理,并将当前回答加入其中以构造验证问题,再通过预测该条件来验证回答。该条件可以是开放域问题中的实体,也可以是数学问题中的数值,只需极少的提示即可识别。我们提出了一个迭代式“先验证后纠正”框架,用于逐步识别并纠正(可能)错误的回答,命名为ProCo。我们在三个推理任务上进行了实验。平均而言,以GPT-3.5-Turbo作为后端LLM的ProCo,与Self-Correct相比,在四个开放域问答数据集上取得了+6.8的精确匹配提升,在三个算术推理数据集上取得了+14.1的准确率提升,并在一个常识推理数据集上取得了+9.6的准确率提升。我们的实现已在 https://wzy6642.github.io/proco.github.io/ 公开发布。
英文摘要:
Intrinsic self-correct was a method that instructed large language models (LLMs) to verify and correct their responses without external feedback. Unfortunately, the study concluded that the LLMs could not self-correct reasoning yet. We find that a simple yet effective verification method can unleash inherent capabilities of the LLMs. That is to mask a key condition in the question, add the current response to construct a verification question, and predict the condition to verify the response. The condition can be an entity in an open-domain question or a numeric value in a math question, which requires minimal effort (via prompting) to identify. We propose an iterative verify-then-correct framework to progressively identify and correct (probably) false responses, named ProCo. We conduct experiments on three reasoning tasks. On average, ProCo, with GPT-3.5-Turbo as the backend LLM, yields $+6.8$ exact match on four open-domain question answering datasets, $+14.1$ accuracy on three arithmetic reasoning datasets, and $+9.6$ accuracy on a commonsense reasoning dataset, compared to Self-Correct. Our implementation is made publicly available at https://wzy6642.github.io/proco.github.io/.
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。