https://terms-en.ai-term-hub.com/zh/tags/content-policy/Recent content in Content Policy on 中文AI术语词典Hugozh-cnSat, 18 Jul 2026 11:44:45 +0000https://terms-en.ai-term-hub.com/zh/terms/uncensored/Sat, 18 Jul 2026 11:37:26 +0000https://terms-en.ai-term-hub.com/zh/terms/uncensored/<h2 id="definition">Definition</h2> <p>在人工智能领域，“无审查”通常描述那些经过微调或修改，以移除或削弱内置安全对齐的模型。这些模型旨在去除内容限制。</p> <h3 id="summary">Summary</h3> <p>指经过修改以绕过安全过滤器和道德准则的人工智能模型。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>安全对齐</li> <li>微调</li> <li>内容审核</li> <li>模型修改</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>研究模型漏洞</li> <li>无限制的创意写作</li> <li>测试安全边界</li> </ul> <h2 id="related-terms">Related Terms</h2> <ul> <li><a href="https://terms-en.ai-term-hub.com/en/terms/jailbreaking-%E8%B6%8A%E7%8B%B1%E6%94%BB%E5%87%BB/">Jailbreaking (越狱攻击)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/alignment-%E5%AF%B9%E9%BD%90/">Alignment (对齐)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/rlhf-%E5%9F%BA%E4%BA%8E%E4%BA%BA%E7%B1%BB%E5%8F%8D%E9%A6%88%E7%9A%84%E5%BC%BA%E5%8C%96%E5%AD%A6%E4%B9%A0/">RLHF (基于人类反馈的强化学习)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/safety-filters-%E5%AE%89%E5%85%A8%E8%BF%87%E6%BB%A4%E5%99%A8/">Safety Filters (安全过滤器)</a></li> </ul>