Stars
Creativity in AI: A Survey of Progresses and Challenges
🌍 Repository for "AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agent", ACL'24 Best Resource Paper.
tiktoken is a fast BPE tokeniser for use with OpenAI's models.
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
About The corresponding code from our paper " Making Reasoning Matter: Measuring and Improving Faithfulness of Chain-of-Thought Reasoning" . Do not hesitate to open an issue if you run into any tro…
A library for advanced large language model reasoning
Reference implementation for DPO (Direct Preference Optimization)
[ACL 2024] A Survey of Chain of Thought Reasoning: Advances, Frontiers and Future
Reasoning in LLMs: Papers and Resources, including Chain-of-Thought, OpenAI o1, and DeepSeek-R1 🍓
The corresponding code from our paper " Generating Hypothetical Events for Abductive Inference (StarSem 2021)". Do not hesitate to open an issue if you run into any trouble!
A benchmark for assessing the strength of causal relationships between real-world events (EMNLP 2023).
Benchmarking Commonsense Reasoning in Real-World Tasks
About The corresponding code from our paper " REFINER: Reasoning Feedback on Intermediate Representations" (EACL 2024). Do not hesitate to open an issue if you run into any trouble!
The data and implementation for the experiments in the paper "Flows: Building Blocks of Reasoning and Collaborating AI".
🤖🌊 aiFlows: The building blocks of your collaborative AI
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
A beautiful, simple, clean, and responsive Jekyll theme for academics
We want to try and evaluate LLMs using Knowledge Graphs
[Paper List] Papers integrating knowledge graphs (KGs) and large language models (LLMs)
A central, open resource for data and tools related to chain-of-thought reasoning in large language models. Developed @ Samwald research group: https://samwald.info/
The data and the PyTorch implementation for the models and experiments in the paper "Language Model Decoding as Likelihood–Utility Alignment".
Holistic Evaluation of Language Models (HELM) is an open source Python framework created by the Center for Research on Foundation Models (CRFM) at Stanford for holistic, reproducible and transparen…