XLANG NLP Lab

All

17 repositories

Spider2
Public
Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows
HTML
•
Apache License 2.0
•14•208•20•0•Updated Dec 3, 2024Dec 3, 2024
OSWorld
Public
[NeurIPS 2024] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
agent cli benchmark natural-language-processing gui reinforcement-learning artificial-intelligence code-generation language-model vlm
Python
•
Apache License 2.0
•161•1.4k•30•0•Updated Nov 29, 2024Nov 29, 2024
Pai-Megatron-Patch
Public
The official repo of Pai-Megatron-Patch for LLM & VLM large scale training developed by Alibaba Cloud.
Python
•
Apache License 2.0
•105•0•0•0•Updated Nov 27, 2024Nov 27, 2024
OpenAgents
Public
[COLM 2024] OpenAgents: An Open Platform for Language Agents in the Wild
agent ui code-generation gpt language-model hacktoberfest assistant-chat-bots semantic-parsing llm tool-learning
Python
•
Apache License 2.0
•447•4k•10•2•Updated Nov 18, 2024Nov 18, 2024
DS-1000
Public
[ICML 2023] Data and code release for the paper "DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation".
data-science benchmark code-generation semantic-parsing large-language-models
Python
•
Creative Commons Attribution Share Alike 4.0 International
•26•224•2•0•Updated Oct 30, 2024Oct 30, 2024
BRIGHT
Public
BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval
benchmark retrieval reasoning
Python
•
Creative Commons Attribution 4.0 International
•1•59•0•0•Updated Oct 22, 2024Oct 22, 2024
text2reward
Public
[ICLR 2024] Code for the paper "Text2Reward: Automated Dense Reward Function Generation for Reinforcement Learning"
agent reinforcement-learning robotics code-generation language-model
Jupyter Notebook
•8•130•1•0•Updated Oct 22, 2024Oct 22, 2024
Spider2-V
Public
[NeurIPS 2024] Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows?
agent natural-language-processing gui artificial-intelligence code-generation multi-modal vlm llm data-science-and-engineering
Jupyter Notebook
•
Apache License 2.0
•7•110•1•0•Updated Aug 26, 2024Aug 26, 2024
instructor-embedding
Public
[ACL 2023] One Embedder, Any Task: Instruction-Finetuned Text Embeddings
information-retrieval text-classification embeddings language-model text-embedding text-clustering text-semantic-similarity text-evaluation prompt-retrieval text-reranking
Python
•
Apache License 2.0
•135•1.9k•32•1•Updated Aug 25, 2024Aug 25, 2024
arks
Public
Python
•
Apache License 2.0
•6•50•3•0•Updated Jun 16, 2024Jun 16, 2024
xlang-paper-reading
Public
Paper collection on building and evaluating language model agents via executable language grounding
agent code-generation tool-use neural-symbolic large-language-models complex-reasoning language-agent llm-robotics web-grounding reinforcement-learning
12•341•0•0•Updated Apr 29, 2024Apr 29, 2024
batch-prompting
Public
[EMNLP 2023 Industry Track] A simple prompting approach that enables the LLMs to run inference in batches.
Python
•5•71•2•1•Updated Mar 8, 2024Mar 8, 2024
.github
Public
0•1•0•0•Updated Oct 19, 2023Oct 19, 2023
Binder
Public
[ICLR 2023] Code for the paper "Binding Language Models in Symbolic Languages"
natural-language-processing openai question-answering language-model fact-verification language-binding prompt-learning in-context-learning structured-knowledge-grounding symbolic-language
Python
•
Apache License 2.0
•35•302•0•0•Updated Aug 25, 2023Aug 25, 2023
UnifiedSKG
Public
[EMNLP 2022] Unifying and multi-tasking structured knowledge grounding with language models
natural-language-processing text-generation question-answering semantic-parsing multi-task-learning fact-verification data-to-text huggingface-transformers prompt-learning huggingface-datasets
Python
•
Apache License 2.0
•58•550•4•0•Updated Aug 22, 2023Aug 22, 2023
icl-selective-annotation
Public
[ICLR 2023] Code for our paper "Selective Annotation Makes Language Models Better Few-Shot Learners"
nlp natural-language-processing language-model active-learning sample-selection in-context-learning
Python
•16•107•1•0•Updated Jul 15, 2023Jul 15, 2023
diagrams_toolkit
Public
Source code for diagrams in the paper of NLPers from HKU.
latex matplotlib toolkit paper
Python
•
MIT License
•1•5•0•0•Updated Apr 15, 2022Apr 15, 2022