For the convenience of anonymous review, this repo stores the data necessary to fully understand the content of the paper.

Codebase for running (conditional) probing experiments

Training Sparse Autoencoders on Language Models

跨语言对齐词向量中日词汇意义研究相关资源

Model interpretability and understanding for PyTorch

Function Vectors in Large Language Models (ICLR 2024)

Exercise Solutions for All of Statistics (Larry Wasserman)

Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes

A light & simple & responsive page for academic websites on Hexo, crafted from academicpages on Jekyll.

pyro教程文档翻译

[LAK25] Human-AI Collaborative Essay Scoring: A Dual-Process Framework with LLMs

Examples and guides for using the OpenAI API

This is the data associated with the PERSUADE Corpus 2.0 version

Ollama Python library

Deep universal probabilistic programming with Python and PyTorch

Bayesian Modeling and Probabilistic Programming in Python

A PyTorch implementation of "Variational Item Response Theory: Fast Accurate, and Expressive"

An Item Response Theory Package for Python

Bayesian IRT models in Python

This project provides an Ancient Chinese Allusion Resource Library to facilitate the automatic analysis of allusions in classical texts and to support research in humanities and language education.

chinsese vocabulary of register

This is a code example repo for the NLP course offered by the Institute of Chinese Information Processing of BNU.

Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders'

Python ROUGE Score Implementation for Chinese Language Task (official rouge score)