As a relative quality comparison of model responses, human and Large Language Model (LLM) preferences serve as common alignment goals in model fine-tuning and criteria in evaluation. Yet, these preferences merely reflect broad tendencies, resulting in less explainable and controllable models with potential safety risks. In this work, we dissect the preferences of human and 32 different LLMs to understand their quantitative composition, using annotations from real-world user-model conversations for a fine-grained, scenario-wise analysis. We find that humans are less sensitive to errors, favor responses that support their stances, and show clear dislike when models admit their limits. On the contrary, advanced LLMs like GPT-4-Turbo emphasize correctness, clarity, and harmlessness more. Additionally, LLMs of similar sizes tend to exhibit similar preferences, regardless of their training methods, and fine-tuning for alignment does not significantly alter the preferences of pretrained-only LLMs. Finally, we show that preference-based evaluation can be intentionally manipulated. In both training-free and training-based settings, aligning a model with the preferences of judges boosts scores, while injecting the least preferred properties lowers them. This results in notable score shifts: up to 0.59 on MT-Bench (1-10 scale) and 31.94 on AlpacaEval 2.0 (0-100 scale), highlighting the significant impact of this strategic adaptation. Interactive Demo: https://huggingface.co/spaces/GAIR/Preference-Dissection-Visualization Dataset: https://huggingface.co/datasets/GAIR/preference-dissection Code: https://github.com/GAIR-NLP/Preference-Dissection

通过对人类和重要语言模型的偏好进行细致分析，研究发现人类对错误不太敏感，倾向于支持他们的观点的回答，并且当模型承认其局限性时显示出明显的不喜欢。相反地，高级语言模型如GPT-4-Turbo更强调正确性、清晰度和无害性。此外，相似大小的语言模型往往表现出类似的偏好，无论它们的训练方法如何，并且对于仅预训练的语言模型来说，通过对齐进行微调并不显著改变其偏好。最后，研究发现基于偏好的评估可以被有意地操纵，将模型与评委的偏好保持一致将提高评分，而注入评委最不喜欢的属性将降低评分。这导致了显著的评分变化，例如在MT-Bench上高达0.59分（1-10分制），在AlpacaEval 2.0上高达31.94分（0-100分制），突显了这种战略性调整的重要影响。

解剖人类和LLM偏好