大语言模型能识别你的偏好吗？评估大语言模型中的个性化偏好遵循能力
Do LLMs Recognize Your Preferences? Evaluating Personalized Preference Following in LLMs
AI总结：
针对LLMs个性化响应用户偏好能力有限的问题，本文提出PrefEval基准（含3000对偏好-查询对、20个主题），评估10个LLMs的偏好遵循能力，发现现有模型表现不足但微调可提升，为个性化对话代理研究提供工具。
摘要：
大语言模型（LLMs）越来越多地被用作聊天机器人，但它们根据用户偏好个性化响应的能力仍然有限。我们引入PrefEval基准，用于评估LLMs在长上下文对话场景中推断、记忆和遵循用户偏好的能力。PrefEval包含3000个手动整理的用户偏好与查询对，涵盖20个主题，以显式和隐式形式包含用户个性化或偏好信息，并通过生成和分类任务评估LLM性能。我们用PrefEval评估了10个开源和专有LLMs在多会话对话中上述偏好遵循能力，上下文长度可达100k tokens，还测试了各种提示、迭代反馈和检索增强生成方法。基准测试显示，最先进的LLMs在对话中主动遵循用户偏好面临重大挑战：零样本设置下，大多数模型在仅10轮（约3k tokens）时偏好遵循准确率低于10%；即使使用高级提示和检索方法，长上下文对话中的偏好遵循仍会下降。此外，我们发现基于PrefEval微调能显著提升性能。我们认为PrefEval是衡量、理解和增强LLMs偏好遵循能力的宝贵资源，为个性化对话代理铺路。代码和数据集见https://prefeval.github.io/。
英文摘要：
Large Language Models (LLMs) are increasingly used as chatbots, yet their ability to personalize responses to user preferences remains limited. We introduce PrefEval, a benchmark for evaluating LLMs' ability to infer, memorize and adhere to user preferences in a long-context conversational setting. PrefEval comprises 3,000 manually curated user preference and query pairs spanning 20 topics. PrefEval contains user personalization or preference information in both explicit and implicit forms, and evaluates LLM performance using a generation and a classification task. With PrefEval, we evaluated the aforementioned preference following capabilities of 10 open-source and proprietary LLMs in multi-session conversations with varying context lengths up to 100k tokens. We benchmark with various prompting, iterative feedback, and retrieval-augmented generation methods. Our benchmarking effort reveals that state-of-the-art LLMs face significant challenges in proactively following users' preferences during conversations. In particular, in zero-shot settings, preference following accuracy falls below 10% at merely 10 turns (~3k tokens) across most evaluated models. Even with advanced prompting and retrieval methods, preference following still deteriorates in long-context conversations. Furthermore, we show that fine-tuning on PrefEval significantly improves performance. We believe PrefEval serves as a valuable resource for measuring, understanding, and enhancing LLMs' preference following abilities, paving the way for personalized conversational agents. Our code and dataset are available at https://prefeval.github.io/.
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。
