evandez / REMEDI
Inspecting and Editing Knowledge Representations in Language Models
☆111Updated last year
Alternatives and similar repositories for REMEDI:
Users that are interested in REMEDI are comparing it to the libraries listed below
- [ICML 2023] Code for our paper “Compositional Exemplars for In-context Learning”.☆95Updated last year
- Github repository for "FELM: Benchmarking Factuality Evaluation of Large Language Models" (NeurIPS 2023)☆57Updated last year
- contrastive decoding☆190Updated 2 years ago
- The accompanying code for "Transformer Feed-Forward Layers Are Key-Value Memories". Mor Geva, Roei Schuster, Jonathan Berant, and Omer Le…☆89Updated 3 years ago
- Code and data accompanying our paper on arXiv "Faithful Chain-of-Thought Reasoning".☆157Updated 8 months ago
- ☆44Updated 4 months ago
- ☆77Updated last year
- PASTA: Post-hoc Attention Steering for LLMs☆109Updated last month
- For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research.☆82Updated this week
- ☆64Updated 2 years ago
- Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering☆39Updated last month
- This repository includes code for the paper "Does Localization Inform Editing? Surprising Differences in Where Knowledge Is Stored vs. Ca…☆58Updated last year
- Code and Data for "Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answering"☆82Updated 5 months ago
- ☆75Updated 5 months ago
- Semi-Parametric Editing with a Retrieval-Augmented Counterfactual Model☆66Updated 2 years ago
- ☆84Updated 2 years ago
- datasets from the paper "Towards Understanding Sycophancy in Language Models"☆66Updated last year
- ☆47Updated 9 months ago
- Self-Alignment with Principle-Following Reward Models☆150Updated 10 months ago
- [ICLR 2023] Guess the Instruction! Flipped Learning Makes Language Models Stronger Zero-Shot Learners☆113Updated 4 months ago
- Grade-School Math with Irrelevant Context (GSM-IC) benchmark is an arithmetic reasoning dataset built upon GSM8K, by adding irrelevant se…☆58Updated last year
- Official Repo for ICLR 2024 paper MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback by Xingyao Wang*, Ziha…☆110Updated 7 months ago
- ☆61Updated last year
- The GitHub repo for Goal Driven Discovery of Distributional Differences via Language Descriptions☆68Updated last year
- Function Vectors in Large Language Models (ICLR 2024)☆131Updated 3 months ago
- Exploring the Limitations of Large Language Models on Multi-Hop Queries☆20Updated 6 months ago
- About The corresponding code from our paper " REFINER: Reasoning Feedback on Intermediate Representations" (EACL 2024). Do not hesitate t…☆69Updated 10 months ago
- Token-level Reference-free Hallucination Detection☆93Updated last year
- Code of ICLR paper: https://openreview.net/forum?id=-cqvvvb-NkI☆91Updated last year
- Code for the arXiv paper: "LLMs as Factual Reasoners: Insights from Existing Benchmarks and Beyond"☆59Updated 9 months ago