zjunlp / KnowledgeCircuits
[NeurIPS 2024] Knowledge Circuits in Pretrained Transformers
☆120Updated last month
Alternatives and similar repositories for KnowledgeCircuits:
Users that are interested in KnowledgeCircuits are comparing it to the libraries listed below
- Code associated with Tuning Language Models by Proxy (Liu et al., 2024)☆102Updated 9 months ago
- Official Code Repository for LM-Steer Paper: "Word Embeddings Are Steers for Language Models" (ACL 2024 Outstanding Paper Award)☆73Updated 3 months ago
- Function Vectors in Large Language Models (ICLR 2024)☆131Updated 3 months ago
- Code for In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering☆154Updated 3 months ago
- Public code repo for paper "SaySelf: Teaching LLMs to Express Confidence with Self-Reflective Rationales"☆97Updated 3 months ago
- The Paper List on Data Contamination for Large Language Models Evaluation.☆86Updated last week
- open-source code for paper: Retrieval Head Mechanistically Explains Long-Context Factuality☆170Updated 5 months ago
- For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research.☆82Updated this week
- Search, Verify and Feedback: Towards Next Generation Post-training Paradigm of Foundation Models via Verifier Engineering☆54Updated last month
- ☆119Updated last month
- Code and Data for "Long-context LLMs Struggle with Long In-context Learning"☆97Updated 6 months ago
- [NAACL 2024 Outstanding Paper] Source code for the NAACL 2024 paper entitled "R-Tuning: Instructing Large Language Models to Say 'I Don't…☆106Updated 6 months ago
- Benchmarking LLMs with Challenging Tasks from Real Users☆206Updated 2 months ago
- Official github repo for the paper "Compression Represents Intelligence Linearly" [COLM 2024]☆130Updated 3 months ago
- PASTA: Post-hoc Attention Steering for LLMs☆109Updated last month
- ☆159Updated 11 months ago
- A simple toolkit for benchmarking LLMs on mathematical reasoning tasks. 🧮✨☆145Updated 8 months ago
- Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision☆111Updated 4 months ago
- Homepage for ProLong (Princeton long-context language models) and paper "How to Train Long-Context Language Models (Effectively)"☆145Updated last month
- [NeurIPS 2024] The official implementation of paper: Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs.☆88Updated 3 months ago
- Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering☆39Updated last month
- Awesome LLM Self-Consistency: a curated list of Self-consistency in Large Language Models☆85Updated 5 months ago
- Data and code for our paper "Why Does the Effective Context Length of LLMs Fall Short?"☆68Updated last month
- AI Logging for Interpretability and Explainability🔬☆97Updated 7 months ago
- [EMNLP 2023] MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questions☆105Updated 4 months ago
- LoFiT: Localized Fine-tuning on LLM Representations☆30Updated this week
- Official repository for "Scaling Retrieval-Based Langauge Models with a Trillion-Token Datastore".☆153Updated last month
- A dataset of LLM-generated chain-of-thought steps annotated with mistake location.☆77Updated 5 months ago
- Codebase for reproducing the experiments of the semantic uncertainty paper (paragraph-length experiments).☆51Updated 9 months ago
- Interpretable Contrastive Monte Carlo Tree Search Reasoning☆39Updated 2 months ago