20260617:目前有914 页
This commit is contained in:
39
concepts/hallucination-mitigation.md
Normal file
39
concepts/hallucination-mitigation.md
Normal file
@@ -0,0 +1,39 @@
|
||||
---
|
||||
title: "Hallucination Mitigation in LLM Systems"
|
||||
type: concept
|
||||
created: 2026-06-04
|
||||
tags: [hallucination, llm, safety, faithfulness]
|
||||
---
|
||||
|
||||
# Hallucination Mitigation(幻觉抑制)
|
||||
|
||||
**定义**:在 LLM 系统中抑制模型生成不忠实于输入或事实的信息的一组技术和方法。
|
||||
|
||||
## 方法分类
|
||||
|
||||
### 1. 检索锚定
|
||||
- [[rag|RAG]]:通过外部检索提供事实基础
|
||||
- [[content-grounded-retrieval]]:严格限定于提供的内容
|
||||
|
||||
### 2. 推理闸门
|
||||
- [[sufficiency-check|充分性检查]]:评估证据是否充足后再生成
|
||||
- Self-Consistency:多路径采样投票
|
||||
|
||||
### 3. 训练时抑制
|
||||
- [[rlhf|RLHF]]:通过人类偏好对齐减少编造
|
||||
- [[dpo|DPO]]:直接偏好优化
|
||||
- Factuality tuning:事实性微调
|
||||
|
||||
### 4. 推理时控制
|
||||
- 约束解码(constrained decoding)
|
||||
- 引用强制(citation enforcement)
|
||||
|
||||
## IntrAgent 的贡献
|
||||
|
||||
[[intragent|IntrAgent]] 的 [[sufficiency-check|充分性检查]] 属于**推理闸门**类——在生成最终答案前显式评估信息充分性。与 RAG 的隐式可靠性不同,这是一个显式的质量控制步骤。
|
||||
|
||||
## 相关概念
|
||||
|
||||
- [[sufficiency-check]] — 充分性检查作为幻觉抑制闸门
|
||||
- [[content-grounded-retrieval]] — 内容锚定抑制幻觉
|
||||
- [[faithfulness-in-ai]] — AI 忠实性
|
||||
Reference in New Issue
Block a user