thu-coai

A Large-scale Chinese Short-Text Conversation Dataset and Chinese pre-training dialog models

Chinese safety prompts for evaluating and improving the safety of LLMs. 中文安全prompts，用于评估和提升大模型的安全性。

A Large-Scale Chinese Cross-Domain Task-Oriented Dialogue Dataset

Official Repository for "Glyph: Scaling Context Windows via Visual-Text Compression"

[EMNLP'24] CharacterGLM: Customizing Chinese Conversational AI Characters with Large Language Models

KdConv: A Chinese Multi-domain Dialogue Dataset Towards Multi-turn Knowledge-driven Conversation

ConvLab-2: An Open-Source Toolkit for Building, Evaluating, and Diagnosing Dialogue Systems

The official repository of the paper: COLD: A Benchmark for Chinese Offensive Language Detection

Data and codes for ACL 2021 paper: Towards Emotional Support Dialog Systems

EVA: Large-scale Pre-trained Chit-Chat Models

Official github repo for SafetyBench, a comprehensive benchmark to evaluate LLMs' safety. [ACL 2024]

一个中文心理健康支持问答数据集，提供了丰富的援助策略标注。可用于生成富有援助策略的长咨询文本。

AISafetyLab: A comprehensive framework covering safety attack, defense, evaluation and paper list.

ShieldLM: Empowering LLMs as Aligned, Customizable and Explainable Safety Detectors [EMNLP 2024 Findings]

书籍《现代自然语言生成》介绍

This project is a tensorflow implement of our work, CCM (Commonsense Conversational Model).

This project is a tensorflow implement of our work, ECM (emotional chatting machine).

Paper list for open-ended language generation

Official Implementation for the ICML2022 paper "Directed Acyclic Transformer for Non-Autoregressive Machine Translation"

Conversational Toolkit. An Open-Source Toolkit for Fast Development and Fair Evaluation of Text Generation

Official Code for "PPT: Pre-trained Prompt Tuning for Few-shot Learning". ACL 2022

清华大学面向对象程序设计课程 课程材料及答疑

Code for ACL2023 paper: Pre-Training to Learn in Context

Benchmarking Complex Instruction-Following with Multiple Constraints Composition (NeurIPS 2024 Datasets and Benchmarks Track)

Implementation for paper "A Knowledge-Enhanced Pretraining Model for Commonsense Story Generation"

Task-oriented dialog system toolkits

Codes for our paper "SentiLARE: Sentiment-Aware Language Representation Learning with Linguistic Knowledge" (EMNLP 2020)

[ICLR 2025] MiniPLM: Knowledge Distillation for Pre-Training Language Models

Codes for our paper "JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge Graphs" (ACL 2021 Findings)

OPD: Chinese Open-Domain Pre-trained Dialogue Model

UNION: An Unreferenced Metric for Evaluating Open-ended Story Generation

Benchmark for evaluating open-ended generation