A Six-Dimensional Taxonomy of Post-Training Adaptation Techniques with Applications in AI Governance
Fardin Afdideh, Fernando Seoane, Farhad Abtahi
cs.LG
Submitted: 2026-08-06
Code: https://github.com/ki-smile/post-training-taxonomy
License: http://creativecommons.org/licenses/by-sa/4.0/
The gist: Post-training adaptation has become central to modern machine learning practice and includes techniques such as retraining, fine-tuning, parameter-efficient adaptation, alignment, retrieval
Terminology
Abstract
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.
Sources
- Detecting Concept Drift in Neural Networks Using Chi-squared Goodness of Fit Testing
- Constitutional AI: Harmlessness from AI Feedback
- Towards Stable Machine Learning Model Retraining via Slowly Varying Sequences
- On the Opportunities and Risks of Foundation Models
- Extending Context Window of Large Language Models via Positional Interpolation
- Sparse Autoencoders Find Highly Interpretable Features in Language Models
- DELLA-Merging: Reducing Interference in Model Merging through Magnitude-Based Sampling
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
- RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment
- From Local to Global: A Graph RAG Approach to Query-Focused Summarization
- GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
- Retrieval-Augmented Generation for Large Language Models: A Survey
- Dual Decomposition of Weights and Singular Value Low Rank Adaptation
- Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding
- Towards Data Governance of Frontier AI Models
- REINFORCE++: Stabilizing Critic-Free Policy Optimization with Global Advantage Normalization
- On the Trustworthiness of Generative Foundation Models: Guideline, Assessment, and Perspective
- Editing Models with Task Arithmetic
- Averaging Weights Leads to Wider Optima and Better Generalization
- A Rank Stabilization Scaling Factor for Fine-Tuning with LoRA
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks