# CLEAR：按提示词动态调节安全对齐，兼顾模型效用

- 来源：Rohan Paul (@rohanpaul_ai)
- 发布时间：2026-08-30 22:32
- AIHOT 分数：43
- AIHOT 链接：https://aihot.virxact.com/items/cmtfxcjdu01xpro3xdermzn0h
- 原文链接：https://x.com/rohanpaul_ai/status/2094070636847026612

## AI 摘要

斯坦福新论文提出 CLEAR，通过小型门控网络按提示词动态调节独立安全模块的介入程度，冻结原模型以保留良性提示的完整性能。该方法在保持安全性的同时，显著减少全局安全微调带来的效用损失。

## 正文

Safety alignment usually costs utility because the aligned weights apply to every prompt;

New Stanford univ paper finds that scaling the safety update per prompt recovers much of what global tuning gives up.

The problem is that a safety fine-tune changes the model for every input. Harmful or not, every prompt now runs through a safer but weaker model.

CLEAR, proposed in this paper, leaves the original model frozen. A small gate reads each incoming prompt and decides how much of a separate safety module to switch on.

Benign prompts get almost none of it, so they run on the untouched model.

– arxiv. org/abs/2608.21278

Title: "CLEAR: Continuous Latent Adapter Routing for Utility-Preserving LLM Safety Alignment"