EMBRACE：通过将隐式对话与社会规范对齐来塑造包容性意见表示
EMBRACE: Shaping Inclusive Opinion Representation by Aligning Implicit Conversations with Social Norms
AI总结：
本文提出EMBRACE框架，通过将回应立场建模为隐式意见代理并与社会规范对齐，结合PU在线学习和指令微调语言模型评估，以改善对话模型中意见表示的包容性与公平性。
摘要：
塑造包容性表示，使其拥抱多样性并确保公平参与和价值观反映，是许多基于对话的模型的核心目标。然而，许多现有方法依赖于表面化的包容性，即使用用户人口统计信息或社会群体的行为属性。这类方法忽视了对话中嵌入的细微、隐式的意见表达。此外，对显性线索的过度依赖可能加剧错位，并在模型输出中强化有害或刻板化的表示。因此，我们退后一步，认识到公平的包容性需要考虑隐式的意见表达，并利用回应的立场来验证规范性对齐。本研究旨在通过引入一个对齐评估框架来评估意见在自然语言处理或计算模型中的表示方式，该框架突出隐式且常被忽视的对话，并评估规范性社会观点和话语。我们的方法将回应的立场建模为潜在意见的代理，从而能够对多样化社会观点进行细致且反思性的表示。我们使用（i）基于正例-无标注（PU）在线学习和基础分类器，以及（ii）指令微调语言模型来评估训练后的对齐情况，从而对该框架进行评估。通过这种方式，我们为隐式意见如何被（错误）表示提供了一个有原则且结构化的视角，并为实现更具包容性的模型行为提供了一条路径。
英文摘要：
Shaping inclusive representations that embrace diversity and ensure fair participation and reflections of values is at the core of many conversation-based models. However, many existing methods rely on surface inclusion using mention of user demographics or behavioral attributes of social groups. Such methods overlook the nuanced, implicit expression of opinion embedded in conversations. Furthermore, the over-reliance on overt cues can exacerbate misalignment and reinforce harmful or stereotypical representations in model outputs. Thus, we took a step back and recognized that equitable inclusion needs to account for the implicit expression of opinion and use the stance of responses to validate the normative alignment. This study aims to evaluate how opinions are represented in NLP or computational models by introducing an alignment evaluation framework that foregrounds implicit, often overlooked conversations and evaluates the normative social views and discourse. Our approach models the stance of responses as a proxy for the underlying opinion, enabling a considerate and reflective representation of diverse social viewpoints. We evaluate the framework using both (i) positive-unlabeled (PU) online learning with base classifiers, and (ii) instruction-tuned language models to assess post-training alignment. Through this, we provide a principled and structured lens on how implicit opinions are (mis)represented and offer a pathway toward more inclusive model behavior.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
