Artificial intelligence (AI) technologies should adhere to human norms to
better serve our society and avoid disseminating harmful or misleading
information, particularly in Conversational Information Retrieval (CIR).
Previous work, including approaches and datasets, has not always been
successful or sufficiently robust in taking human norms into consideration. To
this end, we introduce a workflow that integrates ethical alignment, with an
initial ethical judgment stage for efficient data screening. To address the
need for ethical judgment in CIR, we present the QA-ETHICS dataset, adapted
from the ETHICS benchmark, which serves as an evaluation tool by unifying
scenarios and label meanings. However, each scenario only considers one ethical
concept. Therefore, we introduce the MP-ETHICS dataset to evaluate a scenario
under multiple ethical concepts, such as justice and Deontology. In addition,
we suggest a new approach that achieves top performance in both binary and
multi-label ethical judgment tasks. Our research provides a practical method
for introducing ethical alignment into the CIR workflow. The data and code are
available at this https URL .

人工智能技术应遵循人类规范，以更好地服务社会，避免传播有害或误导性信息，尤其是在会话式信息检索中。我们提出了一种将伦理对齐与初始伦理判断阶段相结合的工作流程，用于高效的数据筛选。我们提出了 QA-ETHICS 数据集，它源自 ETHICS 基准，并通过统一场景和标签意义作为评估工具。此外，我们还引入了 MP-ETHICS 数据集，以评估多个伦理概念下的场景，如公平和道德规范。此外，我们提出了一种新方法，在二进制和多标签伦理判断任务中取得了最佳性能。我们的研究为将伦理对齐引入会话式信息检索工作流程提供了实用方法。数据和代码可在此 https URL 中获得。

EALM：引入多维伦理对齐于对话式 信息检索

EALM: Introducing Multidimensional Ethical Alignment in Conversational  Information Retrieval

A conversational information retrieval (CIR) system is an information
retrieval (IR) system with a conversational interface which allows users to
interact with the system to seek information via multi-turn conversations of
natural language, in spoken or written form. Recent progress in deep learning
has brought tremendous improvements in natural language processing (NLP) and
conversational AI, leading to a plethora of commercial conversational services
that allow naturally spoken and typed interaction, increasing the need for more
human-centric interactions in IR. As a result, we have witnessed a resurgent
interest in developing modern CIR systems in both research communities and
industry. This book surveys recent advances in CIR, focusing on neural
approaches that have been developed in the last few years. This book is based
on the authors' tutorial at SIGIR'2020 (Gao et al., 2020b), with IR and NLP
communities as the primary target audience. However, audiences with other
background, such as machine learning and human-computer interaction, will also
find it an accessible introduction to CIR. We hope that this book will prove a
valuable resource for students, researchers, and software developers. This
manuscript is a working draft. Comments are welcome.

介绍了近年来发展的神经网络方法在对话式信息检索系统中的应用，并聚焦于自然语言处理，多轮对话，以及以人为中心的交互。

对话式信息检索的神经网络方法

Neural Approaches to Conversational Information Retrieval

This paper presents the participation of NetEase Game AI Lab team for the
ClariQ challenge at Search-oriented Conversational AI (SCAI) EMNLP workshop in
2020. The challenge asks for a complete conversational information retrieval
system that can understanding and generating clarification questions. We
propose a clarifying question selection system which consists of response
understanding, candidate question recalling and clarifying question ranking. We
fine-tune a RoBERTa model to understand user's responses and use an enhanced
BM25 model to recall the candidate questions. In clarifying question ranking
stage, we reconstruct the training dataset and propose two models based on
ELECTRA. Finally we ensemble the models by summing up their output
probabilities and choose the question with the highest probability as the
clarification question. Experiments show that our ensemble ranking model
outperforms in the document relevance task and achieves the best recall@[20,30]
metrics in question relevance task. And in multi-turn conversation evaluation
in stage2, our system achieve the top score of all document relevance metrics.

该论文介绍了 NetEase 游戏 AI 实验室团队参加 2020 年 Search-oriented Conversational AI（SCAI）EMNLP 研讨会 ClariQ 挑战的情况。我们提出了一个澄清问题选择系统，它由回复理解、候选问题回忆和澄清问题排名组成。在实验中，我们使用 RoBERTa 模型来理解用户的回复，并使用 BM25 模型回忆候选问题。在澄清问题排名阶段，我们基于 ELECTRA 提出了两种模型，并将它们的输出概率相加，选择概率最高的问题作为澄清问题。实验结果表明，我们的模型在文档相关性任务中表现优异，且在问题相关性任务中达到了最佳的 recall@[20,30] 指标，而在第二阶段的多轮对话评估中，我们的系统获得了所有文档相关性度量的最高分数。