Nlp Alignment
Best practices for LLM alignment techniques including RLHF, DPO, and instruction tuning.
Install
npx skills add aiming-lab/AutoResearchClaw --skill nlp-alignment -g -a claude-code -y- Repository
- aiming-lab/AutoResearchClaw14.8k
- Category
- AI and agents
- Updated
- 3mo ago
- License
- MIT
- Context cost
- Lightabout 174 tokens
- Runs scripts
- No, instructions only
What it does
Best practices for LLM alignment techniques including RLHF, DPO, and instruction tuning. Use when working on alignment or safety.
LLM Alignment Best Practice
Methods:
- RLHF: Train reward model → PPO fine-tuning (complex but powerful)
- DPO: Direct preference optimization (simpler, no reward model needed)
- GRPO: Group relative policy optimization
- SFT: Supervised fine-tuning as alignment baseline
Training recipe:
- Start with SFT on high-quality instruction data
- DPO: lr=5e-7, beta=0.1, batch_size=64
- PPO: lr=1e-6, clip=0.2, KL coeff=0.02
- Use reference model for KL penalty
- Evaluate on safety benchmarks (TruthfulQA, BBQ, etc.)
Common pitfalls:
- Reward hacking: model finds shortcuts to high reward
- Mode collapse: model generates repetitive outputs
- Catastrophic forgetting: loses general capabilities
