google / belief-localizationLinks
This repository includes code for the paper "Does Localization Inform Editing? Surprising Differences in Where Knowledge Is Stored vs. Can Be Injected in Language Models."
☆61Updated 2 years ago
Alternatives and similar repositories for belief-localization
Users that are interested in belief-localization are comparing it to the libraries listed below
Sorting:
- The accompanying code for "Transformer Feed-Forward Layers Are Key-Value Memories". Mor Geva, Roei Schuster, Jonathan Berant, and Omer Le…☆94Updated 3 years ago
- Inspecting and Editing Knowledge Representations in Language Models☆116Updated 2 years ago
- ☆96Updated last year
- ☆44Updated 11 months ago
- Repo accompanying our paper "Do Llamas Work in English? On the Latent Language of Multilingual Transformers".☆78Updated last year
- [ICLR 2023] Code for our paper "Selective Annotation Makes Language Models Better Few-Shot Learners"☆109Updated 2 years ago
- This repository contains data, code and models for contextual noncompliance.☆24Updated last year
- ☆63Updated 2 years ago
- ☆22Updated 2 years ago
- ☆56Updated 3 months ago
- Synthetic question-answering dataset to formally analyze the chain-of-thought output of large language models on a reasoning task.☆147Updated 10 months ago
- Code for the paper "A Mechanistic Interpretation of Arithmetic Reasoning in Language Models using Causal Mediation Analysis"☆19Updated 2 months ago
- Code for "Tracing Knowledge in Language Models Back to the Training Data"☆39Updated 2 years ago
- [ICML 2023] Code for our paper “Compositional Exemplars for In-context Learning”.☆102Updated 2 years ago
- Semi-Parametric Editing with a Retrieval-Augmented Counterfactual Model☆68Updated 2 years ago
- ☆30Updated last year
- ☆110Updated 3 years ago
- Repo for the paper "Large Language Models Struggle to Learn Long-Tail Knowledge"☆77Updated 2 years ago
- The Unreliability of Explanations in Few-shot Prompting for Textual Reasoning (NeurIPS 2022)☆16Updated 2 years ago
- PASTA: Post-hoc Attention Steering for LLMs☆122Updated 9 months ago
- [NeurIPS 2023 D&B Track] Code and data for paper "Revisiting Out-of-distribution Robustness in NLP: Benchmarks, Analysis, and LLMs Evalua…☆34Updated 2 years ago
- ☆54Updated 2 years ago
- Easy-to-use MIRAGE code for faithful answer attribution in RAG applications. Paper: https://aclanthology.org/2024.emnlp-main.347/☆25Updated 5 months ago
- Grade-School Math with Irrelevant Context (GSM-IC) benchmark is an arithmetic reasoning dataset built upon GSM8K, by adding irrelevant se…☆60Updated 2 years ago
- A Kernel-Based View of Language Model Fine-Tuning https://arxiv.org/abs/2210.05643☆78Updated last year
- A library for efficient patching and automatic circuit discovery.☆76Updated last month
- Exploring the Limitations of Large Language Models on Multi-Hop Queries☆27Updated 5 months ago
- [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering☆63Updated 9 months ago
- Github repository for "FELM: Benchmarking Factuality Evaluation of Large Language Models" (NeurIPS 2023)☆59Updated last year
- Providing the answer to "How to do patching on all available SAEs on GPT-2?". It is an official repository of the implementation of the p…☆12Updated 7 months ago