调温度能提升大模型输出与人类意见的对齐度。
Understanding The Effect Of Temperature On Alignment With Human Opinions
- 通过调整采样温度和概率参数获取意见分布。
- 在主观任务中比直接提示更贴近人类观点。
- 适合研究模型对齐与人类主观性的学者。
随着大语言模型能力的提升，近期研究关注其反映何种人类意见以及如何有效提取对齐的意见分布。我们对三种简单方法进行了实证分析，并在多种指标下评估结果。研究表明，通过简单参数调整的采样与对数概率方法，在主观任务中可生成比直接提示更对齐人类意见的输出。然而，假设模型反映人类意见可能过于局限，凸显了进一步研究人类主观性如何影响模型不确定性的必要性。
原文摘要 · Abstract (English)
With the increasing capabilities of LLMs, recent studies focus on understanding whose opinions are represented by them and how to effectively extract aligned opinion distributions. We conducted an empirical analysis of three straightforward methods for obtaining distributions and evaluated the results across a variety of metrics. Our findings suggest that sampling and log-probability approaches with simple parameter adjustments can return better aligned outputs in subjective tasks compared to direct prompting. Yet, assuming models reflect human opinions may be limiting, highlighting the need for further research on how human subjectivity affects model uncertainty.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。