Large language models (LLMs) have been shown to perform better when asked to
reason step-by-step before answering a question. However, it is unclear to what
degree the model's final answer is faithful to the stated reasoning steps. In
this paper, we perform a causal mediation analysis on twelve LLMs to examine
how intermediate reasoning steps generated by the LLM influence the final
outcome and find that LLMs do not reliably use their intermediate reasoning
steps when generating an answer. To address this issue, we introduce FRODO, a
framework to tailor small-sized LMs to generate correct reasoning steps and
robustly reason over these steps. FRODO consists of an inference module that
learns to generate correct reasoning steps using an implicit causal reward
function and a reasoning module that learns to faithfully reason over these
intermediate inferences using a counterfactual and causal preference objective.
Our experiments show that FRODO significantly outperforms four competitive
baselines. Furthermore, FRODO improves the robustness and generalization
ability of the reasoning LM, yielding higher performance on out-of-distribution
test sets. Finally, we find that FRODO's rationales are more faithful to its
final answer predictions than standard supervised fine-tuning.

通过对十二个大型语言模型进行因果中介分析，本文发现大型语言模型在生成最终答案时并不可靠地使用中间推理步骤。为了解决这个问题，我们引入了 FRODO 框架，该框架通过使用隐式因果奖励函数生成正确的推理步骤，以及通过因果和对抗优化目标忠实地进行推理。实验证明，FRODO 显著优于其他四个基线方法，提高了推理语言模型的鲁棒性和泛化能力，在分布外测试集上表现更好。最后，我们发现 FRODO 的解释对最终答案的预测更加可靠。

让推理有意义：衡量和提升思考推理的可靠性

Making Reasoning Matter: Measuring and Improving Faithfulness of  Chain-of-Thought Reasoning

In this paper, we consider fine-grained image object detection in
resource-constrained cases such as edge computing. Deep learning (DL), namely
learning with deep neural networks (DNNs), has become the dominating approach
to object detection. To achieve accurate fine-grained detection, one needs to
employ a large enough DNN model and a vast amount of data annotations, which
brings a challenge for using modern DL object detectors in resource-constrained
cases. To this end, we propose an approach, which leverages commonsense
knowledge to assist a coarse-grained object detector to get accurate
fine-grained detection results. Specifically, we introduce a commonsense
knowledge inference module (CKIM) to translate coarse-grained labels given by a
backbone lightweight coarse-grained DL detector to fine-grained labels. We
consider both crisp-rule and fuzzy-rule based inference in our CKIM; the latter
is used to handle ambiguity in the target semantic labels. We implement our
method based on several modern DL detectors, namely YOLOv4, Mobilenetv3-SSD and
YOLOv7-tiny. Experiment results show that our approach outperforms benchmark
detectors remarkably in terms of accuracy, model size and processing latency.

本文介绍了一种在边缘计算等资源受限情况下的细粒度图像目标检测方法，采用共识知识推理模块辅助轻量级粗粒度目标检测器获得准确的细粒度检测结果，并在多个现代深度学习检测器上进行实验验证。