用分类器动态调整大模型输出，无需微调即可实现个性化生成。
CLIPer: Tailoring Diverse User Preference via Classifier-Guided Inference-Time Personalization
- 通过分类器在推理时实时引导模型生成，实现轻量级个性化。
- 无需微调，在多维偏好下仍能保持高效可控的生成效果。
- 适合需要快速适配用户偏好的对话系统与内容生成场景。
个性化大语言模型可通过匹配用户对帮助性、简洁性和幽默感等偏好的响应，显著提升用户体验。然而，针对所有可能的偏好组合进行微调计算成本高昂且不切实际。本文提出 extbf{CLIPer}（Classifier-guided Inference-time Personalization），一种轻量级个性化方法，利用分类器模型在推理阶段动态引导大模型生成，以适应不同用户偏好。该方法避免了大规模微调，带来可忽略的额外计算开销，同时支持单维与多维偏好的可控、细腻个性化生成。大量实验证明其在个性化语言生成中的可扩展性与有效性。
原文摘要 · Abstract (English)
Personalized LLMs can significantly enhance user experiences by tailoring responses to preferences such as helpfulness, conciseness, and humor. However, fine-tuning models to address all possible combinations of user preferences is computationally expensive and impractical. In this paper, we introduce \textbf{CLIPer}(\textbf{Cl}assifier-guided \textbf{I}nference-time \textbf{Per}sonalization), a lightweight personalization approach that leverages a classifier model to steer LLM generation dynamically to different user preferences at inference time. Our method eliminates the need for extensive fine-tuning, inducing negligible additional computational overhead while enabling more controllable and nuanced personalization across single and multi-dimensional preferences. Comprehensive empirical analyses demonstrate the scalability and effectiveness of our approach in delivering personalized language generation.
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。