One critical issue for chat systems is to stay consistent about preferences,
opinions, beliefs and facts of itself, which has been shown a difficult
problem. In this work, we study methods to assess and bolster utterance
consistency of chat systems. A dataset is first developed for studying the
inconsistencies, where inconsistent dialogue responses, explanations of the
inconsistencies, and recovery utterances are authored by annotators. This
covers the life span of inconsistencies, namely introduction, understanding,
and resolution. Building on this, we introduce a set of tasks centered on
dialogue consistency, specifically focused on its detection and resolution. Our
experimental findings indicate that our dataset significantly helps the
progress in identifying and resolving conversational inconsistencies, and
current popular large language models like ChatGPT which are good at resolving
inconsistencies however still struggle with detection.

研究论文强调了聊天系统的一致性问题，介绍了一个用于研究对话一致性的数据集和一系列任务，实验证明该数据集对于检测和解决会话中的不一致性有显著帮助，同时发现当前流行的大型语言模型如 ChatGPT 在解决不一致性方面表现良好但在检测方面仍存在困难。

不一致的对话回应及其恢复方法

Inconsistent dialogue responses and how to recover from them

We present a novel approach to generating scripts by using agents with
different personality types. To manage character interaction in the script, we
employ simulated dramatic networks. Automatic and human evaluation on multiple
criteria shows that our approach outperforms a vanilla-GPT2-based baseline. We
further introduce a new metric to evaluate dialogue consistency based on
natural language inference and demonstrate its validity.

使用拥有不同人格特征的 agents, 并采用模拟戏剧网络的方法生成剧本，在多项标准上经过自动和人类评估，显示该方法优于基于 vanilla-GPT2 的基线，并引入新的度量标准来评估对话的一致性，并展示其有效性。

对话脚本：使用对话代理生成脚本

DialogueScript: Using Dialogue Agents to Produce a Script

Maintaining a consistent attribute profile is crucial for dialogue agents to
naturally converse with humans. Existing studies on improving attribute
consistency mainly explored how to incorporate attribute information in the
responses, but few efforts have been made to identify the consistency relations
between response and attribute profile. To facilitate the study of profile
consistency identification, we create a large-scale human-annotated dataset
with over 110K single-turn conversations and their key-value attribute
profiles. Explicit relation between response and profile is manually labeled.
We also propose a key-value structure information enriched BERT model to
identify the profile consistency, and it gained improvements over strong
baselines. Further evaluations on downstream tasks demonstrate that the profile
consistency identification model is conducive for improving dialogue
consistency.

通过创建人工注释的数据集并利用 Bert 模型识别属性一致性，本文旨在提高对话代理与人类的属性一致性并进一步证明该模型有助于提高对话的一致性。