benlipkin / probsem
Probabilistic LLM evaluations. [CogSci2023; ACL2023]
☆72Updated 3 months ago
Related projects ⓘ
Alternatives and complementary repositories for probsem
- Code repository for the c-BTM paper☆105Updated last year
- The GitHub repo for Goal Driven Discovery of Distributional Differences via Language Descriptions☆68Updated last year
- ☆46Updated this week
- [ICML 2023] "Outline, Then Details: Syntactically Guided Coarse-To-Fine Code Generation", Wenqing Zheng, S P Sharan, Ajay Kumar Jaiswal, …☆37Updated last year
- Experiments with generating opensource language model assistants☆97Updated last year
- ☆71Updated 6 months ago
- ☆86Updated 5 months ago
- Mechanistic Interpretability for Transformer Models☆49Updated 2 years ago
- ☆91Updated last week
- One stop shop for all things carp☆59Updated 2 years ago
- This repository contains code for cleaning your training data of benchmark data to help combat data snooping.☆25Updated last year
- datasets from the paper "Towards Understanding Sycophancy in Language Models"☆62Updated last year
- ☆22Updated last year
- Erasing concepts from neural representations with provable guarantees☆209Updated last week
- Code and Data Repo for the CoNLL Paper -- Future Lens: Anticipating Subsequent Tokens from a Single Hidden State☆17Updated 10 months ago
- Utilities for the HuggingFace transformers library☆61Updated last year
- Demonstration that finetuning RoPE model on larger sequences than the pre-trained model adapts the model context limit☆63Updated last year
- LLM sampling method for enforcing syntax adherence in generated output☆22Updated last year
- TART: A plug-and-play Transformer module for task-agnostic reasoning☆190Updated last year
- Factored Cognition Primer: How to write compositional language model programs☆48Updated last year
- A dataset of alignment research and code to reproduce it☆69Updated last year
- ☆68Updated 3 months ago
- A repository for transformer critique learning and generation☆86Updated 11 months ago
- A domain-specific probabilistic programming language for modeling and inference with language models☆112Updated last year
- Inspecting and Editing Knowledge Representations in Language Models☆108Updated last year
- Repository containing the SPIN experiments on the DIBT 10k ranked prompts☆23Updated 8 months ago
- Experiments for efforts to train a new and improved t5☆76Updated 7 months ago
- Lightweight tools for quick and easy LLM demo's☆26Updated last month