Code and example data for the paper: Rule Based Rewards for Language Model Safety
☆210Jul 19, 2024Updated 2 years ago
Alternatives and similar repositories for safety-rbr-code-and-data
Users that are interested in safety-rbr-code-and-data are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆16Jul 23, 2024Updated 2 years ago
- Independent robustness evaluation of Improving Alignment and Robustness with Short Circuiting☆18Apr 15, 2025Updated last year
- Improving Alignment and Robustness with Circuit Breakers☆270Sep 24, 2024Updated 2 years ago
- ☆21Nov 3, 2024Updated last year
- ☆166Nov 23, 2024Updated last year
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- RewardBench: the first evaluation tool for reward models.☆743Updated this week
- Code for SafeMERGE (ACL 2026).☆15Oct 2, 2026Updated 2 weeks ago
- ☆34Oct 2, 2024Updated 2 years ago
- Recipes to train reward model for RLHF.☆1,546Apr 24, 2025Updated last year
- [ICLR 2025] On Evluating the Durability of Safegurads for Open-Weight LLMs☆13Jun 20, 2025Updated last year
- Adversarial Attacks on GPT-4 via Simple Random Search [Dec 2023]☆43Apr 28, 2024Updated 2 years ago
- Human preference data for "Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback"☆1,856Jun 17, 2025Updated last year
- Learning from preferences is a common paradigm for fine-tuning language models. Yet, many algorithmic design decisions come into play. Ou…☆32Apr 20, 2024Updated 2 years ago
- ☆29Oct 6, 2024Updated 2 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Code for paper: "Executing Arithmetic: Fine-Tuning Large Language Models as Turing Machines"☆10Oct 11, 2024Updated 2 years ago
- Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".☆155Mar 9, 2024Updated 2 years ago
- [NeurIPS'25] Official codebase for "SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution"☆720Mar 16, 2025Updated last year
- ☆49Oct 1, 2024Updated 2 years ago
- ICLR2024 Paper. Showing properties of safety tuning and exaggerated safety.☆96May 9, 2024Updated 2 years ago
- ☆59Sep 2, 2024Updated 2 years ago
- ☆25Sep 5, 2024Updated 2 years ago
- Scalable toolkit for efficient model alignment☆852Oct 6, 2025Updated last year
- Package to optimize Adversarial Attacks against (Large) Language Models with Varied Objectives☆70Feb 22, 2024Updated 2 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- 800,000 step-level correctness labels on LLM solutions to MATH problems☆2,154Jun 1, 2023Updated 3 years ago
- ☆607Jul 19, 2024Updated 2 years ago
- Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback☆1,620Nov 24, 2025Updated 10 months ago
- ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search (NeurIPS 2024)☆712Jan 20, 2025Updated last year
- [NeurIPS 2024 Oral] Aligner: Efficient Alignment by Learning to Correct☆196Jan 16, 2025Updated last year
- [AAAI'26 Oral] Official Implementation of STAR-1: Safer Alignment of Reasoning LLMs with 1K Data☆38Apr 7, 2025Updated last year
- [ICLR 2024] This is the official implementation for the paper: "Beyond imitation: Leveraging fine-grained quality signals for alignment"☆11May 5, 2024Updated 2 years ago
- A recipe for online RLHF and online iterative DPO.☆545Dec 28, 2024Updated last year
- [NeurIPS'24] Official code for *🎯DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving*☆120Dec 10, 2024Updated last year
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- ☆1,083Mar 6, 2024Updated 2 years ago
- Official Repository for The Paper: Safety Alignment Should Be Made More Than Just a Few Tokens Deep☆192Apr 23, 2025Updated last year
- We jailbreak GPT-3.5 Turbo’s safety guardrails by fine-tuning it on only 10 adversarially designed examples, at a cost of less than $0.20…☆361Feb 23, 2024Updated 2 years ago
- HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal☆1,074Aug 16, 2024Updated 2 years ago
- (ICML 2024) Alphazero-like Tree-Search can guide large language model decoding and training☆286May 26, 2024Updated 2 years ago
- Code for Paper (Policy Optimization in RLHF: The Impact of Out-of-preference Data)☆29Dec 19, 2023Updated 2 years ago
- ☆101Jun 27, 2024Updated 2 years ago