☆15Feb 5, 2025Updated last year
Alternatives and similar repositories for sycophancy-interpretability
Users that are interested in sycophancy-interpretability are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Our research proposes a novel MoGU framework that improves LLMs' safety while preserving their usability.☆17Jan 14, 2025Updated last year
- Decomposing and measuring evaluation awareness in existing benchmarks and our proposed EvalAwareBench.☆19Jun 1, 2026Updated 2 months ago
- Code for safety test in "Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates"☆22Sep 21, 2025Updated 11 months ago
- ☆15May 7, 2022Updated 4 years ago
- Code for evaluating AI systems on the MASK honesty benchmark.☆25Mar 6, 2025Updated last year
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Multi-Layer Sparse Autoencoders (ICLR 2025)☆30Feb 6, 2026Updated 6 months ago
- Automatic Idiomatic Expression Detection☆13Sep 26, 2021Updated 4 years ago
- Code for SafeMERGE (ICLR 2025).☆15Apr 1, 2025Updated last year
- Code and Data for WWW'23 paper Reinforcement Learning-based Counter-Misinformation Response Generation: A Case Study of COVID-19 Vaccine …☆27Jun 28, 2023Updated 3 years ago
- libGDX module for RxJava☆13Oct 23, 2014Updated 11 years ago
- [ACL 2025] LongSafety: Evaluating Long-Context Safety of Large Language Models☆16Jun 18, 2025Updated last year
- Official implementation repository for the paper Towards General Conceptual Model Editing via Adversarial Representation Engineering.☆20Dec 6, 2024Updated last year
- [EMNLP 2025] Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment☆16Jul 22, 2025Updated last year
- Submission archive for the MS MARCO passage ranking leaderboard☆13Apr 21, 2023Updated 3 years ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Python Von Mises Kernel Density Estimator implementation☆11Jun 15, 2017Updated 9 years ago
- Official code for PLoP☆20Mar 6, 2026Updated 5 months ago
- Data and Baselines for AStitchInLanguageModels dataset☆13Oct 31, 2022Updated 3 years ago
- DIALKI: Knowledge Identification in Conversational Systems through Dialogue-Document Contextualization☆10Aug 3, 2022Updated 4 years ago
- ☆14May 26, 2021Updated 5 years ago
- Official repository for our EACL 2023 paper "LongEval: Guidelines for Human Evaluation of Faithfulness in Long-form Summarization" (https…☆45Aug 10, 2024Updated 2 years ago
- ☆11May 11, 2022Updated 4 years ago
- Fine-Tuning Pre-trained Transformers into Decaying Fast Weights☆20Oct 9, 2022Updated 3 years ago
- Official reposity for paper "High-Dimension Human Value Representation in Large Language Models" (NAACL'25 Main)☆23Jul 9, 2024Updated 2 years ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- simple "image2pipe" ffmpeg wrapper for python☆18Aug 30, 2024Updated last year
- Test equality between a black-box LLM API and a reference distribution☆20Oct 29, 2024Updated last year
- Multi-dimensional analysis of orthogonal safety directions in LLM alignment☆23Jun 12, 2026Updated 2 months ago
- ☆22May 23, 2025Updated last year
- Tensorflow implementation of "Tackling the Generative Learning Trilemma with Denoising Diffusion GANs" (ICLR 2022 Spotlight)☆21Aug 3, 2022Updated 4 years ago
- Your finetuned model's back to its original safety standards faster than you can say "SafetyLock"!☆11Oct 16, 2024Updated last year
- Code to reproduce key results accompanying "SAEs (usually) Transfer Between Base and Chat Models"☆13Jul 18, 2024Updated 2 years ago
- This is the official code for the paper "Lazy Safety Alignment for Large Language Models against Harmful Fine-tuning" (NeurIPS2024)☆29Sep 10, 2024Updated last year
- ☆24Mar 21, 2025Updated last year
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Python implementation of Gnutella for CS 114 P2P systems☆12Mar 23, 2012Updated 14 years ago
- Bipedal Skills Benchmark for Reinforcement Learning☆26Oct 27, 2022Updated 3 years ago
- DIVE: Scaling Diversity in Agentic Task Synthesis for Generalizable Tool Use☆29Mar 13, 2026Updated 5 months ago
- ☆67May 18, 2023Updated 3 years ago
- Safe Unlearning: A Surprisingly Effective and Generalizable Solution to Defend Against Jailbreak Attacks☆33Jul 9, 2024Updated 2 years ago
- Small Reward Models via Backward Inference☆22May 25, 2026Updated 2 months ago
- ☆11May 19, 2021Updated 5 years ago