centerforaisafety / wmdp

Related projects: ⓘ

• paul-rottger / exaggerated-safety
  Röttger et al. (2023): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"
  ☆55Updated 8 months ago
• GraySwanAI / circuit-breakers
  Improving Alignment and Robustness with Circuit Breakers
  ☆124Updated 2 months ago
• ejones313 / auditing-llms
  ☆47Updated last year
• mlcommons / modelbench
  Run safety benchmarks against AI models and view detailed reports showing how well they performed.
  ☆50Updated this week
• thestephencasper / explore_establish_exploit_llms
  ☆30Updated last year
• azshue / AutoPoison
  The official repository of the paper "On the Exploitability of Instruction Tuning".
  ☆56Updated 7 months ago
• andyrdt / refusal_direction
  Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".
  ☆76Updated 3 weeks ago
• vinid / safety-tuned-llamas
  ICLR2024 Paper. Showing properties of safety tuning and exaggerated safety.
  ☆61Updated 4 months ago
• locuslab / tofu
  Landing Page for TOFU
  ☆79Updated 3 months ago
• XuandongZhao / weak-to-strong
  Weak-to-Strong Jailbreaking on Large Language Models
  ☆62Updated 6 months ago
• rishub-tamirisa / tamper-resistance
  Official Repository for "Tamper-Resistant Safeguards for Open-Weight LLMs"
  ☆34Updated 3 weeks ago
• ykwon0407 / DataInf
  DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models (ICLR 2024)
  ☆48Updated 5 months ago
• Vaidehi99 / InfoDeletionAttacks
  ☆37Updated 10 months ago
• logix-project / logix
  AI Logging for Interpretability and Explainability🔬
  ☆74Updated 3 months ago
• peterljq / Parsimonious-Concept-Engineering
  Parsimonious Concept Engineering (PaCE) uses sparse coding on a large-scale concept dictionary to effectively improve the trustworthiness…
  ☆25Updated 3 months ago
• ucl-dark / llm_debate
  Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"
  ☆70Updated 5 months ago
• centerforaisafety / tdc2023-starter-kit
  This is the starter kit for the Trojan Detection Challenge 2023 (LLM Edition), a NeurIPS 2023 competition.
  ☆77Updated 4 months ago
• ajyl / dpo_toxic
  A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.
  ☆46Updated last month
• nrimsky / LM-exp
  LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces
  ☆73Updated 11 months ago
• SafeAILab / RAIN
  [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning
  ☆79Updated 3 months ago
• JonasGeiping / carving
  Package to optimize Adversarial Attacks against (Large) Language Models with Varied Objectives
  ☆59Updated 6 months ago
• chrisliu298 / awesome-representation-engineering
  A resource repository for representation engineering in large language models
  ☆36Updated last week
• iamgroot42 / mimir
  Python package for measuring memorization in LLMs.
  ☆107Updated this week
• Princeton-SysML / Jailbreak_LLM
  ☆143Updated 9 months ago
• Thartvigsen / GRACE
  [NeurIPS'23] Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors
  ☆64Updated 6 months ago
• ericwtodd / function_vectors
  Function Vectors in Large Language Models (ICLR 2024)
  ☆107Updated last month
• max-andr / adversarial-random-search-gpt4
  Adversarial Attacks on GPT-4 via Simple Random Search [Dec 2023]
  ☆41Updated 4 months ago
• ryoungj / ToolEmu
  A language model (LM)-based emulation framework for identifying the risks of LM agents with tool use
  ☆106Updated 5 months ago
• JailbreakBench / jailbreakbench
  An Open Robustness Benchmark for Jailbreaking Language Models [arXiv 2024]
  ☆169Updated last month
• Improbable-AI / curiosity_redteam
  Official implementation of ICLR'24 paper, "Curiosity-driven Red Teaming for Large Language Models" (https://openreview.net/pdf?id=4KqkizX…
  ☆57Updated 6 months ago