HKU NLP Group

ChunkLlama

[ICML'24] Data and code for our paper "Training-Free Long-Context Scaling of Large Language Models"

diffusion-of-thoughts

Code for the paper "Diffusion of Thoughts: Chain-of-Thought Reasoning in Diffusion Language Models"

efficient-attention

[EVA ICLR'23; LARA ICML'22] Efficient attention mechanisms via control variates, random features, and importance sampling

HumanPrompt

A framework for human-readable prompt-based method with large language models. Specially designed for researchers. (Deprecated, check out LangChain for better usage!)

icl-ceil

[ICML 2023] Code for our paper “Compositional Exemplars for In-context Learning”.

ProGen

[EMNLP-2022 Findings] Code for paper “ProGen: Progressive Zero-shot Dataset Generation via In-context Feedback”.

reparam-discrete-diffusion

Reparameterized Discrete Diffusion Models for Text Generation

RSA

Retrieved Sequence Augmentation for Protein Representation Learning

subgoal-theorem-prover

Code for the paper "Decomposing the Enigma: Subgoal-based Demonstration Learning for Formal Theorem Proving"

SymGen

[EMNLP'23] Code for Generating Data for Symbolic Language with Large Language Models

HKUNLP/ChunkLlama

[ICML'24] Data and code for our paper "Training-Free Long-Context Scaling of Large Language Models"

HKUNLP/HumanPrompt

A framework for human-readable prompt-based method with large language models. Specially designed for researchers. (Deprecated, check out LangChain for better usage!)

HKUNLP/icl-ceil

[ICML 2023] Code for our paper “Compositional Exemplars for In-context Learning”.

HKUNLP/reparam-discrete-diffusion

Reparameterized Discrete Diffusion Models for Text Generation

HKUNLP/efficient-attention

[EVA ICLR'23; LARA ICML'22] Efficient attention mechanisms via control variates, random features, and importance sampling

HKUNLP/diffusion-of-thoughts

Code for the paper "Diffusion of Thoughts: Chain-of-Thought Reasoning in Diffusion Language Models"

HKUNLP/RSA

Retrieved Sequence Augmentation for Protein Representation Learning

HKUNLP/ProGen

[EMNLP-2022 Findings] Code for paper “ProGen: Progressive Zero-shot Dataset Generation via In-context Feedback”.

HKUNLP/subgoal-theorem-prover

Code for the paper "Decomposing the Enigma: Subgoal-based Demonstration Learning for Formal Theorem Proving"

HKUNLP/SymGen

[EMNLP'23] Code for Generating Data for Symbolic Language with Large Language Models

HKUNLP/ZeroGen

[EMNLP 2022] Code for our paper “ZeroGen: Efficient Zero-shot Learning via Dataset Generation”.

HKUNLP/multilingual-transfer

Code for paper ”Language Versatilists vs. Specialists: An Empirical Revisiting on Multilingual Transfer Ability“

HKUNLP/hkunlp.github.io

Website for HKU NLP group (under construction)

HKUNLP/UnifiedSKGsite

A Portal Site for Structured Knowledge Grounding(SKG) Resources.

HKUNLP/SunGen

HKUNLP/.github

HKUNLP/GIMLET

The code for GIMLET: A Unified Graph-Text Model for Instruction-Based Molecule Zero-Shot Learning