mlcommons / modelbenchLinks
Run safety benchmarks against AI models and view detailed reports showing how well they performed.
☆118Updated last week
Alternatives and similar repositories for modelbench
Users that are interested in modelbench are comparing it to the libraries listed below
Sorting:
- Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs☆104Updated last year
- Improving Alignment and Robustness with Circuit Breakers☆255Updated last year
- A simple evaluation of generative language models and safety classifiers.☆84Updated last month
- ☆153Updated 3 years ago
- Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆123Updated 11 months ago
- A Comprehensive Assessment of Trustworthiness in GPT Models☆311Updated last year
- Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".☆124Updated last year
- WMDP is a LLM proxy benchmark for hazardous knowledge in bio, cyber, and chemical security. We also release code for RMU, an unlearning m…☆157Updated 7 months ago
- ☆60Updated 2 years ago
- ☆108Updated last year
- [ICLR'24 Spotlight] A language model (LM)-based emulation framework for identifying the risks of LM agents with tool use☆179Updated last year
- Package to optimize Adversarial Attacks against (Large) Language Models with Varied Objectives☆70Updated last year
- Codes and datasets of the paper Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment☆108Updated last year
- Collection of evals for Inspect AI☆344Updated this week
- datasets from the paper "Towards Understanding Sycophancy in Language Models"☆101Updated 2 years ago
- Evaluating LLMs with fewer examples☆169Updated last year
- The Prism Alignment Project☆87Updated last year
- ☆262Updated 10 months ago
- Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"☆124Updated last year
- ☆228Updated 4 years ago
- Do-Not-Answer: A Dataset for Evaluating Safeguards in LLMs☆306Updated last year
- ☆43Updated 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…☆336Updated last year
- Benchmarking LLMs with Challenging Tasks from Real Users☆245Updated last year
- Make it easy to automatically and uniformly measure the behavior of many AI Systems.☆26Updated last year
- WorkBench: a Benchmark Dataset for Agents in a Realistic Workplace Setting.☆60Updated 3 weeks ago
- ☆116Updated last year
- Data and code for the preprint "In-Context Learning with Long-Context Models: An In-Depth Exploration"☆42Updated last year
- The code for the paper ROUTERBENCH: A Benchmark for Multi-LLM Routing System☆153Updated last year
- ☆31Updated 2 years ago