研究人员推出了PLURAL，这是一个旨在解决大型语言模型（LLMs）中西方偏见问题的新数据集。该数据集源自涵盖92个国家的综合价值观调查（IVS），包含约50万个合成偏好三元组。PLURAL旨在改善大型语言模型与全球多元价值观的对齐，在自动化评估中平均绝对误差减少了27.7%，并在印度、巴西和日本的人工评估中获得了积极反馈。 AI
影响 可能导致更具全球代表性且偏见更少的人工智能模型。
排序理由 该集群描述了一个新的学术数据集和研究论文，重点是改进人工智能对齐。
在 Hugging Face Daily Papers 阅读 →
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
arXiv:2607.08034v1 Announce Type: cross Abstract: Large language models (LLMs) are used worldwide, yet disproportionately reflect Western values, limiting their ability to represent diverse value systems. We introduce PLURAL, a large-scale, value-focused preference dataset ground…
Large language models (LLMs) are used worldwide, yet disproportionately reflect Western values, limiting their ability to represent diverse value systems. We introduce PLURAL, a large-scale, value-focused preference dataset grounded in the Integrated Values Survey (IVS), a nation…
Large language models (LLMs) are used worldwide, yet disproportionately reflect Western values, limiting their ability to represent diverse value systems. We introduce PLURAL, a large-scale, value-focused preference dataset grounded in the Integrated Values Survey (IVS), a nation…