牛哥精选 · 半年

📋 全部 🤖 AI·大模型 ⚡ 效率工具 📝 深度技术 🚀 产品观察 💰 商业科技 🔓 开源项目 🎨 设计创意 📖 阅读推荐 🏷 资源合集 🌱 成长效率

🤖 AI·大模型 arXiv AI 2026-06-23

When Preferences Fail to Become Incentives: A Utility-Behavior Gap in Large Language Models

揭秘大模型“口是心非”：偏好未化为激励，效用与行为存在隐性鸿沟

arXiv:2606.22974v1 Announce Type: new Abstract: Recent work on preference elicitation in large language models (LLMs) has demonstrated that, when give…

大模型对齐 rlhf 偏好优化行为缺口 arxiv论文

🤖 AI·大模型 arXiv AI 2026-06-10

An LLM-Native Psychometric Instrument Does Not Predict LLM Behavior: Evidence Across 25 Models

LLM自述心理特质与实际行为大相径庭，25个模型验证存在“言行不一”的自我报告-行为鸿沟。

arXiv:2606.09843v1 Announce Type: cross Abstract: Large language models (LLMs) produce stable self-reports on personality inventories, but these self-…

llm 心理测量行为差距自我报告 ai评估

📅 日期

2026-05-20 2026-05-19

🐂 牛哥精选

When Preferences Fail to Become Incentives: A Utility-Behavior Gap in Large Language Models

An LLM-Native Psychometric Instrument Does Not Predict LLM Behavior: Evidence Across 25 Models

📅 日期