Large Language Models (LLMs) work surprisingly well for some complex
reasoning problems via chain-of-thought (CoT) or tree-of-thought (ToT), but the
underlying reasons remain unclear. We seek to understand the performance of
these methods by conducting experimental case studies and linking the outcomes
to sample and computational complexity in machine learning. We found that if
problems can be decomposed into a sequence of reasoning steps and learning to
predict the next step has a low sample and computational complexity, explicitly
outlining the reasoning chain with all necessary information for predicting the
next step may improve performance. Conversely, for problems where predicting
the next step is computationally hard, adopting ToT may yield better reasoning
outcomes than attempting to formulate a short reasoning chain.

通过进行实验案例研究并将结果与机器学习中的样本和计算复杂性联系起来，我们发现如果问题可以分解成一系列推理步骤，并且学习预测下一步具有较低的样本和计算复杂性，明确列出推理链与预测下一步所需的所有必要信息可能会改善性能，相反，对于计算复杂的问题，采用树状推理可能比尝试形成简短的推理链更好地产生推理结果。

关于 LLMs 的推理和规划经验复杂性的研究

On the Empirical Complexity of Reasoning and Planning in LLMs

Argumentative explainable AI has been advocated by several in recent years,
with an increasing interest on explaining the reasoning outcomes of
Argumentation Frameworks (AFs). While there is a considerable body of research
on qualitatively explaining the reasoning outcomes of AFs with
debates/disputes/dialogues in the spirit of \emph{extension-based semantics},
explaining the quantitative reasoning outcomes of AFs under \emph{gradual
semantics} has not received much attention, despite widespread use in
applications. In this paper, we contribute to filling this gap by proposing a
novel theory of \emph{Argument Attribution Explanations (AAEs)} by
incorporating the spirit of feature attribution from machine learning in the
context of Quantitative Bipolar Argumentation Frameworks (QBAFs): whereas
feature attribution is used to determine the influence of features towards
outputs of machine learning models, AAEs are used to determine the influence of
arguments towards \emph{topic argument}s of interest. We study desirable
properties of AAEs, including some new ones and some partially adapted from the
literature to our setting. To demonstrate the applicability of our AAEs in
practice, we conclude by carrying out two case studies in the scenarios of fake
news detection and movie recommender systems.

解释性 AI 的一个关键问题是如何解释 Argumentation Frameworks (AFs) 的推理结果，而定量推理结果在 gradual semantics 下的解释尚未得到广泛关注。本文提出了一个新的 Argument Attribution Explanations (AAEs) 理论，通过在 Quantitative Bipolar Argumentation Frameworks (QBAFs) 中引入机器学习中的特征归因理念，研究 AAEs 的理论性质，并通过两个案例研究验证了 AAEs 在假新闻检测和电影推荐系统中的应用性。