DecipherPref：通过GPT-4分析人类偏好判断中的影响因素
DecipherPref: Analyzing Influential Factors in Human Preference Judgments via GPT-4
AI总结：
本文利用BTL模型分析OpenAI发布的人类成对偏好判断，揭示不同任务中最受与最不受偏好因素的规律，为构建平衡的偏好评估数据集提供指导。
摘要：
人类偏好判断在引导大语言模型（LLMs）生成符合人类价值观的输出方面起着关键作用。在摘要任务中，人类评估也被用来比较不同系统的输出，以补充现有的自动评估指标。然而，尽管这些判断具有重要意义，针对这些成对或k-wise比较的研究仍然有限。输出长度、信息量、流畅性和事实一致性等因素的集体影响和相对重要性仍未得到充分理解。此外，是否还有其他隐藏因素在影响人类判断也不清楚。本文对OpenAI发布的一组成对人类判断进行了深入分析。利用Bradley-Terry-Luce（BTL）模型，我们揭示了这些人类判断中蕴含的内在偏好。我们发现，最受偏好的因素因任务和体裁而异，而最不受偏好的因素往往一致，例如输出过于简短、包含过多偏离主题的内容或产生幻觉事实。我们的研究结果对人类偏好评估中平衡数据集的构建具有启示意义，这是塑造未来大语言模型行为的关键步骤。
英文摘要：
Human preference judgments are pivotal in guiding large language models (LLMs) to produce outputs that align with human values. Human evaluations are also used in summarization tasks to compare outputs from various systems, complementing existing automatic metrics. Despite their significance, however, there has been limited research probing these pairwise or $k$-wise comparisons. The collective impact and relative importance of factors such as output length, informativeness, fluency, and factual consistency are still not well understood. It is also unclear if there are other hidden factors influencing human judgments. In this paper, we conduct an in-depth examination of a collection of pairwise human judgments released by OpenAI. Utilizing the Bradley-Terry-Luce (BTL) model, we reveal the inherent preferences embedded in these human judgments. We find that the most favored factors vary across tasks and genres, whereas the least favored factors tend to be consistent, e.g., outputs are too brief, contain excessive off-focus content or hallucinated facts. Our findings have implications on the construction of balanced datasets in human preference evaluations, which is a crucial step in shaping the behaviors of future LLMs.
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。
