While Large language models (LLMs) have the capability to iteratively reflect
on their own outputs, recent studies have observed their struggles with
knowledge-rich problems without access to external resources. In addition to
the inefficiency of LLMs in self-assessment, we also observe that LLMs struggle
to revisit their predictions despite receiving explicit negative feedback.
Therefore, We propose Mirror, a Multiple-perspective self-reflection method for
knowledge-rich reasoning, to avoid getting stuck at a particular reflection
iteration. Mirror enables LLMs to reflect from multiple-perspective clues,
achieved through a heuristic interaction between a Navigator and a Reasoner. It
guides agents toward diverse yet plausibly reliable reasoning trajectory
without access to ground truth by encouraging (1) diversity of directions
generated by Navigator and (2) agreement among strategically induced
perturbations in responses generated by the Reasoner. The experiments on five
reasoning datasets demonstrate that Mirror's superiority over several
contemporary self-reflection approaches. Additionally, the ablation study
studies clearly indicate that our strategies alleviate the aforementioned
challenges.

提出了一种多视角自反思方法 Mirror，通过导航器和推理器之间的启发式相互作用，使 LLMs 能够从多个视角线索进行反思，从而避免陷入特定的反思迭代，实验结果表明 Mirror 在几个当代自反思方法上具有优势，并且消除了之前面临的挑战。

镜像：一种适用于知识丰富推理的多角度自省方法

Mirror: A Multiple-perspective Self-Reflection Method for Knowledge-rich  Reasoning

Hate speech detection is complex; it relies on commonsense reasoning,
knowledge of stereotypes, and an understanding of social nuance that differs
from one culture to the next. It is also difficult to collect a large-scale
hate speech annotated dataset. In this work, we frame this problem as a
few-shot learning task, and show significant gains with decomposing the task
into its "constituent" parts. In addition, we see that infusing knowledge from
reasoning datasets (e.g. Atomic2020) improves the performance even further.
Moreover, we observe that the trained models generalize to out-of-distribution
datasets, showing the superiority of task decomposition and knowledge infusion
compared to previously used methods. Concretely, our method outperforms the
baseline by 17.83% absolute gain in the 16-shot case.

本文根据学科本质，将恶意言论检测问题视为少样本学习任务，并表明将该问题分解成其 “组成” 部分可以取得显着的收益。此外，我们发现从推理数据集（例如 Atomic2020）注入知识可以进一步提高性能。此外，我们观察到训练模型可以推广到分布之外的数据集中，表明任务分解和知识注入相比以前使用的方法具有优越性。具体而言，我们的方法在 16 个样本的情况下比基线提高了 17.83％的绝对收益。