Ryo Kamoi

llm-self-correction-papers. List of papers on Self-Correction of LLMs.

ppg_vc. Implementation of voice conversion system utilizing phonetic posteriorgrams (status: archive)

dcnn_textvae. TensorFlow implementation of "Improved Variational Autoencoders for Text Modeling using Dilated Convolutions"

wice. This repository contains the dataset and code for "WiCE: Real-World Entailment for Claims in Wikipedia" in EMNLP 2023.

hybrid_textvae. TensorFlow implementation of "A Hybrid Convolutional Variational Autoencoder for Text Generation"

pytorch_influence_functions. This is a PyTorch reimplementation of Influence Functions from the ICML2017 best paper: Understanding Black-box Predictions via Influence Functions by Pang Wei Koh and Percy Liang.

sg_langevin. Implementation of Stochastic Gradient Langevin Dynamics

original_textvae. TensorFlow implementation of "Generating Sentences from a Continuous Space"

test_pytorch_influence_functions. Test code for pytorch_influence_functions

voice_analysis_app. Voice analysis application with GMM

QA-metrics-human-annotation. Human Generated Questions in ''Shortcomings of Question Answering Based Factuality Frameworks for Error Localization'' (EACL2023)

ryokamoi.

llm_wrapper. This repository includes an unofficial wrapper for LLMs, such as OpenAI API and HuggingFace models, mainly for caching LLM responses to avoid duplicate inference with the identical prompts.