meg-tong / sycophancy-eval
datasets from the paper "Towards Understanding Sycophancy in Language Models"
☆59Updated 10 months ago
Related projects: ⓘ
- 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
- ☆74Updated this week
- The GitHub repo for Goal Driven Discovery of Distributional Differences via Language Descriptions☆68Updated last year
- Inspecting and Editing Knowledge Representations in Language Models☆105Updated last year
- Steering Llama 2 with Contrastive Activation Addition☆83Updated 3 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆52Updated last month
- ☆64Updated last month
- Function Vectors in Large Language Models (ICLR 2024)☆107Updated last month
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆73Updated 11 months ago
- 👻 Code and benchmark for our EMNLP 2023 paper - "FANToM: A Benchmark for Stress-testing Machine Theory of Mind in Interactions"☆49Updated 3 months ago
- ☆87Updated 2 months ago
- Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".☆76Updated 3 weeks ago
- Code and data accompanying our paper on arXiv "Faithful Chain-of-Thought Reasoning".☆151Updated 4 months ago
- Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"☆70Updated 5 months ago
- CausalGym: Benchmarking causal interpretability methods on linguistic tasks☆28Updated 6 months ago
- AI Logging for Interpretability and Explainability🔬☆74Updated 3 months ago
- ☆69Updated 10 months ago
- A repository for transformer critique learning and generation☆84Updated 9 months ago
- The Official Repository for "Bring Your Own Data! Self-Supervised Evaluation for Large Language Models"☆109Updated 11 months ago
- Scalable Meta-Evaluation of LLMs as Evaluators☆39Updated 7 months ago
- Röttger et al. (2023): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆55Updated 8 months ago
- ☆29Updated 10 months ago
- Evaluating LLMs with fewer examples☆131Updated 5 months ago
- ☆92Updated 4 months ago
- Algebraic value editing in pretrained language models☆54Updated 10 months ago
- ☆75Updated this week
- Code and Data Repo for the CoNLL Paper -- Future Lens: Anticipating Subsequent Tokens from a Single Hidden State☆14Updated 8 months ago
- Code repository for the paper "Mission: Impossible Language Models".☆27Updated 8 months ago
- ☆53Updated 2 months ago
- PASTA: Post-hoc Attention Steering for LLMs☆96Updated last week