ajyl / dpo_toxicLinks
A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.
☆74Updated 4 months ago
Alternatives and similar repositories for dpo_toxic
Users that are interested in dpo_toxic are comparing it to the libraries listed below
Sorting:
- [ICLR 2025] General-purpose activation steering library☆87Updated last week
- ☆43Updated last year
- Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆106Updated 5 months ago
- ☆96Updated last year
- [ICML 2024] Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications☆81Updated 4 months ago
- ☆60Updated last year
- ☆29Updated last year
- ☆47Updated last year
- A resource repository for representation engineering in large language models☆129Updated 8 months ago
- Function Vectors in Large Language Models (ICLR 2024)☆175Updated 3 months ago
- ☆52Updated 2 years ago
- [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering☆62Updated 8 months ago
- ☆60Updated 4 months ago
- DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models (ICLR 2024)☆73Updated 10 months ago
- [ICLR 2025] Official Repository for "Tamper-Resistant Safeguards for Open-Weight LLMs"☆59Updated last month
- ☆51Updated last year
- Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization☆30Updated last year
- [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning☆96Updated last year
- Steering Llama 2 with Contrastive Activation Addition☆167Updated last year
- ☆45Updated last week
- AI Logging for Interpretability and Explainability🔬☆124Updated last year
- [ICLR'25 Spotlight] Min-K%++: Improved baseline for detecting pre-training data of LLMs☆41Updated 2 months ago
- Official code for SEAL: Steerable Reasoning Calibration of Large Language Models for Free☆37Updated 3 months ago
- ☆35Updated 7 months ago
- Repo accompanying our paper "Do Llamas Work in English? On the Latent Language of Multilingual Transformers".☆78Updated last year
- ConceptVectors Benchmark and Code for the paper "Intrinsic Evaluation of Unlearning Using Parametric Knowledge Traces"☆36Updated 5 months ago
- ☆41Updated 10 months ago
- Algebraic value editing in pretrained language models☆65Updated last year
- Augmenting Statistical Models with Natural Language Parameters☆27Updated 10 months ago
- ☆55Updated 2 years ago