---
title: "A Six-Dimensional Taxonomy of Post-Training Adaptation Techniques with Applications in AI Governance"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2608.06246v1"
permalink: "https://feed.astralor.com/items/itm_ce00c7b3c386b5fe6eda188e"
published: "2026-08-06T16:32:26.000Z"
score: 75
channel: "ai"
tags: ["AI Governance","Taxonomy","Post-training Adaptation","Fine-tuning","Retrieval-Augmented"]
---

# A Six-Dimensional Taxonomy of Post-Training Adaptation Techniques with Applications in AI Governance

## AI commentary

> What stands out is its attempt to end the misuse of terms like fine-tuning. For teams auditing model changes, this taxonomy can serve as a template for internal documentation. It also highlights open challenges—such as inference-time adaptation and multimodal adaptation—that are likely to define the next wave of research.

## At a glance

Post-training adaptation has become central to modern machine learning, covering retraining, fine-tuning, parameter-efficient adaptation, alignment, retrieval augmentation, model editing, unlearning, calibration, and multimodal instruction tuning. However, the literature remains fragmented, making it difficult to compare methods or describe how a trained model has been modified. This survey synthesizes the field and introduces a six-dimensional taxonomy organized by mechanism, goal, data requirement, persistence, structural scope, and model type. It distinguishes commonly conflated terms such as fine-tuning, retrieval augmentation, and prompting, and shows how adaptation strategies evolve from traditional machine learning to deep learning, foundation models, large language models, and multimodal large language models. It also maps relationships including inheritance, supersession, hybridization, and layered deployment stacks. The resulting vocabulary supports technical documentation, model-change tracking, and governance analysis. The survey identifies open challenges in evaluation, reproducibility, persistent inference-time adaptation, unlearning, multimodal adaptation, and governance-aware workflows.

## Key points

- Proposes a six-dimensional taxonomy to unify post-training adaptation terminology.
- Distinguishes easily conflated concepts like fine-tuning, retrieval augmentation, and prompting.
- Maps technique evolution and relationships including inheritance, supersession, hybridization, and layered stacks.
- Identifies open challenges in evaluation, reproducibility, multimodal adaptation, and governance workflows.

## Full text

Post-training adaptation has become central to modern machine learning practice and includes techniques such as retraining, fine-tuning, parameter-efficient adaptation, alignment, retrieval augmentation, model editing, unlearning, calibration, and Multimodal Instruction Tuning. However, the literature remains fragmented across technique families, model classes, and deployment contexts, making it difficult to compare methods or describe how a trained model has been modified. This survey synthesizes the post-training adaptation literature and introduces a six-dimensional taxonomy organized by mechanism, goal, data requirement, persistence, structural scope, and model type. The taxonomy distinguishes commonly conflated terms such as fine-tuning, retrieval augmentation, and prompting, and shows how adaptation strategies evolve from traditional machine learning through deep learning, foundation models, large language models, and multimodal large language models. It also maps relationships among techniques, including inheritance, supersession, hybridization, and layered deployment stacks. The resulting vocabulary can support technical documentation, model-change tracking, and governance analysis. The survey concludes by identifying open challenges in evaluation, reproducibility, persistent inference-time adaptation, unlearning, multimodal adaptation, and governance-aware post-training workflows.

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_ce00c7b3c386b5fe6eda188e