Skip to content
@thu-coai

thu-coai

Conversational AI groups from Tsinghua University

Pinned Loading

  1. CDial-GPT CDial-GPT Public

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

    Python 1.8k 255

  2. CrossWOZ CrossWOZ Public

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

    Python 631 114

  3. KdConv KdConv Public archive

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

    Python 463 62

  4. ConvLab-2 ConvLab-2 Public

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

    Python 450 131

  5. Safety-Prompts Safety-Prompts Public

    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。

    851 80

  6. CharacterGLM-6B CharacterGLM-6B Public

    CharacterGLM: Customizing Chinese Conversational AI Characters with Large Language Models

    Python 395 30

Repositories

Showing 10 of 84 repositories
  • ShieldLM Public

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

    thu-coai/ShieldLM’s past year of commit activity
    Python 139 MIT 6 1 0 Updated Sep 29, 2024
  • CodePlan Public
    thu-coai/CodePlan’s past year of commit activity
    3 0 0 0 Updated Sep 19, 2024
  • PICL Public

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

    thu-coai/PICL’s past year of commit activity
    Python 106 MIT 4 1 1 Updated Jul 26, 2024
  • PsyQA Public

    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。

    thu-coai/PsyQA’s past year of commit activity
    163 14 0 0 Updated Jul 21, 2024
  • thu-coai/ComplexBench’s past year of commit activity
    Python 47 MIT 4 2 0 Updated Jul 16, 2024
  • JailbreakDefense_GoalPriority Public

    [ACL 2024] Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization

    thu-coai/JailbreakDefense_GoalPriority’s past year of commit activity
    Python 11 1 0 0 Updated Jul 9, 2024
  • SafeUnlearning Public

    Safe Unlearning: A Surprisingly Effective and Generalizable Solution to Defend Against Jailbreak Attacks

    thu-coai/SafeUnlearning’s past year of commit activity
    Python 20 1 0 0 Updated Jul 9, 2024
  • thu-coai/CritiqueLLM’s past year of commit activity
    Python 126 4 6 0 Updated Jul 1, 2024
  • AutoDetect Public

    Official github repo for AutoDetect, an automated weakness detection framework for LLMs.

    thu-coai/AutoDetect’s past year of commit activity
    Python 37 MIT 1 0 0 Updated Jun 25, 2024
  • BPO Public
    thu-coai/BPO’s past year of commit activity
    Python 288 Apache-2.0 15 0 0 Updated Jun 24, 2024