恢复的追索权：与生成式语言模型的对话
Recourse for reclamation: Chatting with generative language models
AI总结：
本研究将算法追索权扩展至生成式语言模型，提出动态设置毒性过滤阈值的新机制以提升用户能动性，初步研究证明其可用性优于固定阈值过滤。
摘要：
研究人员和开发者越来越依赖毒性评分来审核生成式语言模型的输出，这适用于客户服务、信息检索和内容生成等场景。然而，毒性评分可能导致相关信息无法访问，使文化规范僵化或“价值锁定”，并阻碍语言恢复过程，特别是对于边缘化群体。在本研究中，我们将算法追索权的概念扩展到生成式语言模型：我们为用户提供了一种新机制，通过动态设置毒性过滤的阈值来实现其期望的预测结果。用户因此相对于与基线系统的交互获得了更多的能动性。一项初步研究（n = 30）支持了我们提出的追索权机制的潜力，表明与固定阈值的模型输出毒性过滤相比，可用性有所提升。未来的工作应探索毒性评分、模型可控性、用户能动性和语言恢复过程的交叉点——特别是关于许多社区在与生成式语言模型交互时遇到的偏见。
英文摘要：
Researchers and developers increasingly rely on toxicity scoring to moderate generative language model outputs, in settings such as customer service, information retrieval, and content generation. However, toxicity scoring may render pertinent information inaccessible, rigidify or "value-lock" cultural norms, and prevent language reclamation processes, particularly for marginalized people. In this work, we extend the concept of algorithmic recourse to generative language models: we provide users a novel mechanism to achieve their desired prediction by dynamically setting thresholds for toxicity filtering. Users thereby exercise increased agency relative to interactions with the baseline system. A pilot study ($n = 30$) supports the potential of our proposed recourse mechanism, indicating improvements in usability compared to fixed-threshold toxicity-filtering of model outputs. Future work should explore the intersection of toxicity scoring, model controllability, user agency, and language reclamation processes -- particularly with regard to the bias that many communities encounter when interacting with generative language models.
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。
