梳理大模型个性化偏好对齐的主流方法与挑战
A Survey on Personalized and Pluralistic Preference Alignment in Large Language Models
- 按训练、推理和用户建模三类归纳对齐技术
- 系统分析各类方法优劣及评估现状
- 适合关注个性化AI与大模型优化的研究者
大语言模型的个性化偏好对齐，即根据个体用户偏好定制模型响应，是自然语言处理与个性化领域的新兴研究方向。本文综述了该领域相关工作，提出一套偏好对齐技术分类体系，涵盖训练阶段、推理阶段以及基于用户建模的方法。我们分析了每类方法的优势与局限，并讨论了当前评估体系、基准数据集及未解问题，为后续研究提供参考。
原文摘要 · Abstract (English)
Personalized preference alignment for large language models (LLMs), the process of tailoring LLMs to individual users' preferences, is an emerging research direction spanning the area of NLP and personalization. In this survey, we present an analysis of works on personalized alignment and modeling for LLMs. We introduce a taxonomy of preference alignment techniques, including training time, inference time, and additionally, user-modeling based methods. We provide analysis and discussion on the strengths and limitations of each group of techniques and then cover evaluation, benchmarks, as well as open problems in the field.
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。