mlcommons / modelbenchLinks
Run safety benchmarks against AI models and view detailed reports showing how well they performed.
☆101Updated last week
Alternatives and similar repositories for modelbench
Users that are interested in modelbench are comparing it to the libraries listed below
Sorting:
- A simple evaluation of generative language models and safety classifiers.☆60Updated last year
- Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs☆89Updated 8 months ago
- Improving Alignment and Robustness with Circuit Breakers☆228Updated 11 months ago
- WMDP is a LLM proxy benchmark for hazardous knowledge in bio, cyber, and chemical security. We also release code for RMU, an unlearning m…☆135Updated 3 months ago
- Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆110Updated 6 months ago
- A Comprehensive Assessment of Trustworthiness in GPT Models☆302Updated 11 months ago
- ☆57Updated 2 years ago
- [ICLR'24 Spotlight] A language model (LM)-based emulation framework for identifying the risks of LM agents with tool use☆159Updated last year
- Codes and datasets of the paper Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment☆103Updated last year
- ☆33Updated last year
- Finding trojans in aligned LLMs. Official repository for the competition hosted at SaTML 2024.☆114Updated last year
- Package to optimize Adversarial Attacks against (Large) Language Models with Varied Objectives☆70Updated last year
- ☆139Updated 3 years ago
- ☆91Updated 9 months ago
- Do-Not-Answer: A Dataset for Evaluating Safeguards in LLMs☆281Updated last year
- Repo for the research paper "SecAlign: Defending Against Prompt Injection with Preference Optimization"☆66Updated last month
- datasets from the paper "Towards Understanding Sycophancy in Language Models"☆89Updated last year
- Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".☆112Updated last year
- ☆31Updated 2 years ago
- 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…☆318Updated last year
- Evaluating LLMs with fewer examples☆160Updated last year
- ☆181Updated last year
- Official Repository for Dataset Inference for LLMs☆37Updated last year
- ICLR2024 Paper. Showing properties of safety tuning and exaggerated safety.☆87Updated last year
- The code for the paper ROUTERBENCH: A Benchmark for Multi-LLM Routing System☆134Updated last year
- Collection of evals for Inspect AI☆211Updated this week
- Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".☆261Updated 2 months ago
- ☆17Updated last year
- Code for the paper "Fishing for Magikarp"☆163Updated 3 months ago
- [ICLR 2025] Official Repository for "Tamper-Resistant Safeguards for Open-Weight LLMs"☆59Updated 2 months ago