tml-epfl / llm-past-tense
Does Refusal Training in LLMs Generalize to the Past Tense? [ICLR 2025]
☆67Updated 2 months ago
Alternatives and similar repositories for llm-past-tense:
Users that are interested in llm-past-tense are comparing it to the libraries listed below
- Weak-to-Strong Jailbreaking on Large Language Models☆72Updated last year
- Package to optimize Adversarial Attacks against (Large) Language Models with Varied Objectives☆68Updated last year
- [NeurIPS 2024] Goldfish Loss: Mitigating Memorization in Generative LLMs☆84Updated 5 months ago
- Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)☆60Updated 3 months ago
- [ICLR 2025] Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates (Oral)☆76Updated 5 months ago
- Independent robustness evaluation of Improving Alignment and Robustness with Short Circuiting☆16Updated 8 months ago
- Improving Alignment and Robustness with Circuit Breakers☆196Updated 6 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…☆110Updated 11 months ago
- ☆169Updated last year
- Adversarial Attacks on GPT-4 via Simple Random Search [Dec 2023]☆43Updated 11 months ago
- [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning☆91Updated 10 months ago
- ☆14Updated 2 weeks ago
- [ICLR 2025] Official Repository for "Tamper-Resistant Safeguards for Open-Weight LLMs"☆53Updated last month
- ☆54Updated 2 years ago
- ☆42Updated 2 months ago
- Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆96Updated last month
- [ICLR 2025] Dissecting Adversarial Robustness of Multimodal LM Agents☆80Updated last month
- Repo for the research paper "SecAlign: Defending Against Prompt Injection with Preference Optimization"☆44Updated last week
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆63Updated 3 weeks ago
- The official repository of the paper "On the Exploitability of Instruction Tuning".☆62Updated last year
- ☆31Updated last year
- PaCE: Parsimonious Concept Engineering for Large Language Models (NeurIPS 2024)☆35Updated 5 months ago
- ConceptVectors Benchmark and Code for the paper "Intrinsic Evaluation of Unlearning Using Parametric Knowledge Traces"☆33Updated 2 months ago
- Improving Your Model Ranking on Chatbot Arena by Vote Rigging☆20Updated last month
- PAL: Proxy-Guided Black-Box Attack on Large Language Models☆50Updated 8 months ago
- Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs☆72Updated 4 months ago
- ☆41Updated last year
- Code to break Llama Guard☆31Updated last year
- [ICML 2024] Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast☆99Updated last year
- Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [ICLR 2025]☆292Updated 2 months ago