ajyl / dpo_toxicLinks
A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.
☆72Updated 3 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:
- ☆44Updated 3 months ago
- ☆40Updated last year
- [ICML 2024] Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications☆79Updated 2 months ago
- General-purpose activation steering library☆78Updated last month
- ☆59Updated 11 months ago
- ☆95Updated last year
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆94Updated last year
- [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering☆60Updated 6 months ago
- Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆98Updated 4 months ago
- ☆35Updated last month
- ☆29Updated last year
- ☆44Updated last year
- A resource repository for representation engineering in large language models☆126Updated 7 months ago
- ☆49Updated last year
- LoFiT: Localized Fine-tuning on LLM Representations☆39Updated 5 months ago
- Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization☆26Updated 10 months ago
- Algebraic value editing in pretrained language models☆65Updated last year
- A library for efficient patching and automatic circuit discovery.☆66Updated 2 months ago
- ☆22Updated 3 months ago
- [ICLR'25 Spotlight] Min-K%++: Improved baseline for detecting pre-training data of LLMs☆39Updated 3 weeks ago
- Steering Llama 2 with Contrastive Activation Addition☆158Updated last year
- ☆16Updated last year
- Code associated with Tuning Language Models by Proxy (Liu et al., 2024)☆112Updated last year
- Augmenting Statistical Models with Natural Language Parameters☆27Updated 9 months ago
- DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models (ICLR 2024)☆70Updated 8 months ago
- Function Vectors in Large Language Models (ICLR 2024)☆170Updated 2 months ago
- Official code for "Decoding-Time Language Model Alignment with Multiple Objectives".☆24Updated 7 months ago
- [ICLR 2025] Official Repository for "Tamper-Resistant Safeguards for Open-Weight LLMs"☆58Updated 2 weeks ago
- ☆41Updated 8 months ago
- [ACL 2024] Code and data for "Machine Unlearning of Pre-trained Large Language Models"☆59Updated 8 months ago