epfl-dlab / llm-latent-languageLinks
Repo accompanying our paper "Do Llamas Work in English? On the Latent Language of Multilingual Transformers".
☆80Updated last year
Alternatives and similar repositories for llm-latent-language
Users that are interested in llm-latent-language are comparing it to the libraries listed below
Sorting:
- ☆97Updated last year
- ☆91Updated last year
- Exploring the Limitations of Large Language Models on Multi-Hop Queries☆27Updated 7 months ago
- The Paper List on Data Contamination for Large Language Models Evaluation.☆99Updated last month
- ☆39Updated last year
- [ICLR 2024] Evaluating Large Language Models at Evaluating Instruction Following☆131Updated last year
- ☆44Updated last year
- GSM-Plus: Data, Code, and Evaluation for Enhancing Robust Mathematical Reasoning in Math Word Problems.☆63Updated last year
- Official repository for ACL 2025 paper "Model Extrapolation Expedites Alignment"☆75Updated 4 months ago
- [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering☆63Updated 10 months ago
- Official Code Repository for LM-Steer Paper: "Word Embeddings Are Steers for Language Models" (ACL 2024 Outstanding Paper Award)☆124Updated 2 months ago
- An open-source library for contamination detection in NLP datasets and Large Language Models (LLMs).☆56Updated last year
- Function Vectors in Large Language Models (ICLR 2024)☆180Updated 5 months ago
- Code for the paper "A Mechanistic Interpretation of Arithmetic Reasoning in Language Models using Causal Mediation Analysis"☆19Updated 3 months ago
- ☆29Updated last year
- [NeurIPS 2024] How do Large Language Models Handle Multilingualism?☆41Updated 10 months ago
- Code associated with Tuning Language Models by Proxy (Liu et al., 2024)☆120Updated last year
- The accompanying code for "Transformer Feed-Forward Layers Are Key-Value Memories". Mor Geva, Roei Schuster, Jonathan Berant, and Omer Le…☆97Updated 4 years ago
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆80Updated 6 months ago
- PASTA: Post-hoc Attention Steering for LLMs☆123Updated 10 months ago
- Semi-Parametric Editing with a Retrieval-Augmented Counterfactual Model☆70Updated 2 years ago
- For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research.☆154Updated this week
- [NeurIPS'23] Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors☆81Updated 9 months ago
- Data and code for the preprint "In-Context Learning with Long-Context Models: An In-Depth Exploration"☆39Updated last year
- Analyzing LLM Alignment via Token distribution shift☆17Updated last year
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆97Updated 2 years ago
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆134Updated 3 months ago
- Grade-School Math with Irrelevant Context (GSM-IC) benchmark is an arithmetic reasoning dataset built upon GSM8K, by adding irrelevant se…☆62Updated 2 years ago
- LoFiT: Localized Fine-tuning on LLM Representations☆41Updated 8 months ago
- Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging☆108Updated last year