Large language models (LLMs) have shown tremendous success in following user
instructions and generating helpful responses. Nevertheless, their robustness
is still far from optimal, as they may generate significantly inconsistent
responses due to minor changes in the verbalized instructions. Recent
literature has explored this inconsistency issue, highlighting the importance
of continued improvement in the robustness of response generation. However,
systematic analysis and solutions are still lacking. In this paper, we
quantitatively define the inconsistency problem and propose a two-stage
training framework consisting of instruction-augmented supervised fine-tuning
and consistency alignment training. The first stage helps a model generalize on
following instructions via similar instruction augmentations. In the second
stage, we improve the diversity and help the model understand which responses
are more aligned with human expectations by differentiating subtle differences
in similar responses. The training process is accomplished by self-rewards
inferred from the trained model at the first stage without referring to
external human preference resources. We conduct extensive experiments on recent
publicly available LLMs on instruction-following tasks and demonstrate the
effectiveness of our training framework.

定义了指令不一致问题并提出了两阶段训练框架，在第一阶段通过相似指令增强帮助模型跟随指令，第二阶段通过区分相似回应中微小差异来提高模型的多样性和人类期望的一致性，并通过自奖励训练过程来验证该框架的有效性。

通过一致对齐提升大型语言模型的鲁棒性

Improving the Robustness of Large Language Models via Consistency  Alignment

The graph-based model can help to detect suspicious fraud online. Owing to
the development of Graph Neural Networks~(GNNs), prior research work has
proposed many GNN-based fraud detection frameworks based on either homogeneous
graphs or heterogeneous graphs. These work follow the existing GNN framework by
aggregating the neighboring information to learn the node embedding, which lays
on the assumption that the neighbors share similar context, features, and
relations. However, the inconsistency problem is hardly investigated, i.e., the
context inconsistency, feature inconsistency, and relation inconsistency. In
this paper, we introduce these inconsistencies and design a new GNN framework,
$\mathsf{GraphConsis}$, to tackle the inconsistency problem: (1) for the
context inconsistency, we propose to combine the context embeddings with node
features, (2) for the feature inconsistency, we design a consistency score to
filter the inconsistent neighbors and generate corresponding sampling
probability, and (3) for the relation inconsistency, we learn a relation
attention weights associated with the sampled nodes. Empirical analysis on four
datasets indicates the inconsistency problem is crucial in a fraud detection
task. The extensive experiments prove the effectiveness of
$\mathsf{GraphConsis}$. We also released a GNN-based fraud detection toolbox
with implementations of SOTA models. The code is available at
this https URL

本文提出了一个新的 GNN 框架 GraphConsis, 以解决在线欺诈检测中的不一致性问题 (包括上下文、特征和关系不一致性)，并在四个数据集上进行实证分析，证明了 GraphConsis 的有效性。