tonychenxyz / selfie
This repository contains the code and data for the paper "SelfIE: Self-Interpretation of Large Language Model Embeddings" by Haozhe Chen, Carl Vondrick, and Chengzhi Mao.
☆30Updated 5 months ago
Related projects: ⓘ
- Parsimonious Concept Engineering (PaCE) uses sparse coding on a large-scale concept dictionary to effectively improve the trustworthiness…☆25Updated 3 months ago
- Codebase for Inference-Time Policy Adapters☆19Updated 10 months ago
- ☆143Updated 9 months ago
- Weak-to-Strong Jailbreaking on Large Language Models☆62Updated 6 months ago
- Code associated with Tuning Language Models by Proxy (Liu et al., 2024)☆84Updated 5 months ago
- Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"☆70Updated 5 months ago
- [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning☆79Updated 3 months ago
- ☆46Updated 2 weeks ago
- ☆16Updated 3 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…☆72Updated 4 months ago
- Knowledge Circuits in Pretrained Transformers☆46Updated this week
- Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding☆89Updated 2 months ago
- ☆8Updated 4 months ago
- Function Vectors in Large Language Models (ICLR 2024)☆107Updated last month
- Flow of Reasoning: Efficient Training of LLM Policy with Diverse Thinking☆25Updated this week
- Official repository for paper "Weak-to-Strong Extrapolation Expedites Alignment"☆62Updated 3 months ago
- 📈 Scaling Laws with Vocabulary: Larger Models Deserve Larger Vocabularies https://arxiv.org/abs/2407.13623☆52Updated 3 weeks ago
- Self-Explore to avoid ️the p️️it! Improving the Reasoning Capabilities of Language Models with Fine-grained Rewards☆39Updated 4 months ago
- Improving Alignment and Robustness with Circuit Breakers☆124Updated 2 months ago
- Algebraic value editing in pretrained language models☆54Updated 10 months ago
- Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"☆56Updated 3 months ago
- ☆37Updated 10 months ago
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆23Updated 3 months ago
- ☆13Updated 2 months ago
- ☆64Updated last month
- Code for In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering☆130Updated 2 months ago
- ☆32Updated 10 months ago
- ☆29Updated last year
- Repository for NPHardEval, a quantified-dynamic benchmark of LLMs☆46Updated 5 months ago
- Scalable Meta-Evaluation of LLMs as Evaluators☆39Updated 7 months ago