LLM Alignment & Preference Optimization

Preference optimization in practice — DPO, SimPO, ORPO, CPO, KTO, reward modeling, and RLHF. What each method does, when it helps, and how to choose between them.

Alignment

DPO: Direct Preference Optimization for LLM Alignment

DPO aligns an LLM to human preferences with no reward model and no RL loop — the objective, the pair format, and when pairs beat labels.

16 min readJun 15, 2026
Alignment

SimPO: Simple Preference Optimization Without Reference Models

SimPO aligns an LLM with no reference model in memory — the length-normalized objective, the data it needs, and when it beats DPO.

12 min readJun 12, 2026
Alignment

ORPO: Odds Ratio Preference Optimization

ORPO folds SFT and preference alignment into a single stage — the odds-ratio objective, the dataset it needs, and when one stage wins.

11 min readJun 10, 2026
Alignment

CPO: Contrastive Preference Optimization for LLM Alignment

CPO pairs a contrastive objective with behavior cloning — chosen responses stay high-probability, rejected ones suppressed — and when that matters.

11 min readJun 8, 2026
Alignment

KTO: Kahneman-Tversky Optimization for AI Alignment

KTO aligns an LLM on binary thumbs-up/down feedback through prospect theory — losses weighted heavier than gains — no pairing required.

12 min readJun 5, 2026
Alignment

Reward Modeling for RLHF: Training Custom Reward Functions

Training a reward model for RLHF — the pipeline it anchors, the preference data it eats, and how it is evaluated before any policy trusts it.

13 min readJun 3, 2026
Alignment

RLHF Methods: Offline Alignment vs Online Reinforcement Learning

Compare offline alignment methods (DPO, SimPO, ORPO, CPO, KTO) with online RL (PPO, GRPO, GKD). Understand when to use each and what is coming to Vidman AI.

13 min readMay 20, 2026
Alignment

Red-Teaming Your LLM Before Users Do

Red-teaming is the review where you attack your own model before users do. The attack catalog, who should run it, and how findings become fixes.

9 min readMay 15, 2026
Alignment

RLVR: Learning With Verifiable Rewards

RLVR trains models on rewards that can be checked, not judged. Where verifiable rewards shine, the reward-hacking traps, and when preferences still win.

9 min readMay 13, 2026