诊断与去偏 GPT2 中的语料库政治偏见与侮辱性语言
Diagnosing and Debiasing Corpus-Based Political Bias and Insults in GPT2
AI总结：
本研究评估诊断-去偏方法在GPT2中缓解侮辱性语言和政治偏见的效果，旨在减少有害文本生成并探讨人机交互的伦理影响。
摘要：
大型语言模型（LLM）在来自互联网的广泛且未经过滤的语料上进行训练是一种常见且有益的做法。因此，LLM 学习并无意中重现了各种类型的偏见，包括暴力、攻击性和有毒语言。然而，近期研究表明，生成式预训练 Transformer（GPT）语言模型能够识别自身的偏见并检测生成内容中的毒性，这一过程被称为自我诊断。作为回应，研究人员开发了一种解码算法，使 LLM 能够自我去偏，即降低其生成有害文本的可能性。本研究调查了诊断-去偏方法在缓解另外两种偏见类型（侮辱性语言和政治偏见）方面的有效性。这两种偏见在话语中经常互换使用，尽管它们可能表现出不同的语义和句法特性。我们旨在为持续调查人机交互的伦理和社会影响的工作做出贡献。
英文摘要：
The training of large language models (LLMs) on extensive, unfiltered corpora sourced from the internet is a common and advantageous practice. Consequently, LLMs have learned and inadvertently reproduced various types of biases, including violent, offensive, and toxic language. However, recent research shows that generative pretrained transformer (GPT) language models can recognize their own biases and detect toxicity in generated content, a process referred to as self-diagnosis. In response, researchers have developed a decoding algorithm that allows LLMs to self-debias, or reduce their likelihood of generating harmful text. This study investigates the efficacy of the diagnosing-debiasing approach in mitigating two additional types of biases: insults and political bias. These biases are often used interchangeably in discourse, despite exhibiting potentially dissimilar semantic and syntactic properties. We aim to contribute to the ongoing effort of investigating the ethical and social implications of human-AI interaction.
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。
