近年来，大型语言模型(LLMs) 的推理能力取得了巨大进步。然而, LLM的推理过程经常表现出不确定性,，其中LLM经常在每个推理步骤中产生大量不同的分支，即使在提供相同的提示输入, 时也是如此，并且某些分支表现出明显令人难以置信的, 甚至荒谬的, 推理链和结果。在本文,中，我们提出了基于图复杂性的UncerTainty(GUT)方法来研究LLM的推理不确定性。 GUT的核心思想是用有向无环图,来表征每个推理链的潜在分支，从而确保所有潜在分支都被全面覆盖在图空间内。在此认识,的基础上，我们进一步构建了两个GUT,模块，即,量化(GUT-Q)模块和优化(GUT-O)模块,，分别用于量化和减少LLM,的推理不确定性。 GUT-Q 通过用图复杂度近似推理空间复杂度来衡量 LLM 推理不确定性。 GUT-O通过将负不确定性视为强化学习中的奖励函数来实现不确定性优化。在四个LLM和五个数据集上进行的实验结果验证了 GUT 的有效性。
Recent years have witnessed great advances in the reasoning ability of Large Language Models (LLMs). However, the reasoning processes of LLMs often exhibit uncertainty, where LLMs often produce a proliferation of divergent branches at each reasoning step even when fed the same prompting inputs, and certain branches exhibit evidently incredible, even nonsensical, reasoning chains and results. In this paper, we propose the Graph-complexity-based UncerTainty (GUT) method for investigating the reasoning uncertainty of LLMs. The key idea of GUT is to characterize the potential branches of each reasoning chain with a directed acyclic graph, thereby ensuring that all potential branches are comprehensively covered within the graph space. Building upon this recognition, we further build two modules of GUT, that is, a Quantification (GUT-Q) module and an Optimization (GUT-O) module, for quantifying and reducing the reasoning uncertainty of LLMs, respectively. GUT-Q measures LLM reasoning uncertainty by approximating the reasoning space complexity with graph complexity. GUT-O implements uncertainty optimization by treating negative uncertainty as the reward function in reinforcement learning. Experimental results conducted on four LLMs and five datasets validate the effectiveness of GUT.
科目:人工智能(cs.AI)
Subjects: Artificial Intelligence (cs.AI)