语言模型与现实世界用户期望的期望对齐
Expectation Alignment of Language Models for Real-World User Expectations
浏览论文内容
中文总结 AI 辅助
研究LLMs是否满足用户期望，提出提取期望程序并引入ExpectBench基准，分析发现LLMs存在问题，进而提出LENS框架，可让模型内化期望以生成更契合的响应，凸显明确建模用户期望对实现现实人机对齐的重要性。
中文摘要 AI 辅助
大型语言模型（LLMs）在标准基准测试中表现出色，但它们是否真正满足用户期望仍未得到充分探索。现有评估方法无法捕捉真实人类期望的多样性和微妙之处。本文首次对现实世界中LLM交互的用户期望进行系统研究，提出提取语义丰富期望的原则性程序并引入基于真实用户期望的基准ExpectBench。分析表明当前LLMs难以满足和预测用户期望。在此基础上提出轻量级潜在期望感知响应生成框架LENS，能使模型内化用户期望并生成更符合的响应。
英文摘要
Large language models (LLMs) have demonstrated remarkable performance on standard benchmarks, yet it remains largely unexplored whether they truly meet user expectations. Existing evaluation approaches, relying on model heuristics, expert rubrics, or user simulation, fail to capture the diversity and subtlety of real human expectations, causing models to appear competent while misaligning with what users actually seek. We present the first systematic study of user expectations in real-world LLM interactions, proposing a principled procedure to extract semantically rich expectations and introducing ExpectBench, a benchmark grounded in real user expectations. Analyses reveal that current LLMs struggle to satisfy and anticipate what users hope to obtain, highlighting a fundamental source of misalignment. Building on these observations, we propose LENS, a lightweight latent expectation-aware response generation framework. LENS enables models to internalize user expectations and generate better-aligned responses, consistently improving expectation satisfaction and underscoring the importance of explicitly modeling user expectations for realistic human-AI alignment.
