Skip to content
Agentmart
Submit a tool

nlp-alignment

Best practices for LLM alignment techniques including RLHF, DPO, and instruction tuning.

Skill by researchclaw

IndexedMIT
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/raja21068-nlp-alignment

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Best practices for LLM alignment techniques including RLHF, DPO, and instruction tuning. Use when working on alignment or safety.

Use cases: ml

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/nlp-alignment

What's inside

Skill name
nlp-alignment
Description
Best practices for LLM alignment techniques including RLHF, DPO, and instruction tuning. Use when working on alignment or safety.
License
MIT
Metadata
author: researchclaw · version: 1.0 · category: domain · priority: 4 · references: Ouyang et al., Training language models to follow instructions, NeurIPS 2022; Rafailov et al., DPO, NeurIPS 2023 · trigger-keywords: alignment,rlhf,dpo,reward model,preference,instruction tuning,safety · applicable-stages: 9,10
Instructions
20 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

## 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

From raja21068/AutoScholar, MIT.

More from raja21068/AutoScholar

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Apr 12, 2026 (6 months ago)

From GitHub (fetched Oct 24, 2026).

Details

Version
1.0
License
MIT
Repository
github.com/raja21068/AutoScholar
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from researchclaw

Cite this page

nlp-alignment skill. Agent Mart. https://agentmart.dev/skills/raja21068-nlp-alignment (last updated 2026-10-24)