Pinned Repositories
BPO
CDial-GPT
A Large-scale Chinese Short-Text Conversation Dataset and Chinese pre-training dialog models
CharacterGLM-6B
[EMNLP'24] CharacterGLM: Customizing Chinese Conversational AI Characters with Large Language Models
COLDataset
The official repository of the paper: COLD: A Benchmark for Chinese Offensive Language Detection
ConvLab-2
ConvLab-2: An Open-Source Toolkit for Building, Evaluating, and Diagnosing Dialogue Systems
CrossWOZ
A Large-Scale Chinese Cross-Domain Task-Oriented Dialogue Dataset
Emotional-Support-Conversation
Data and codes for ACL 2021 paper: Towards Emotional Support Dialog Systems
EVA
EVA: Large-scale Pre-trained Chit-Chat Models
KdConv
KdConv: A Chinese Multi-domain Dialogue Dataset Towards Multi-turn Knowledge-driven Conversation
Safety-Prompts
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。
thu-coai's Repositories
thu-coai/Safety-Prompts
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。
thu-coai/CrossWOZ
A Large-Scale Chinese Cross-Domain Task-Oriented Dialogue Dataset
thu-coai/ConvLab-2
ConvLab-2: An Open-Source Toolkit for Building, Evaluating, and Diagnosing Dialogue Systems
thu-coai/CharacterGLM-6B
[EMNLP'24] CharacterGLM: Customizing Chinese Conversational AI Characters with Large Language Models
thu-coai/BPO
thu-coai/Emotional-Support-Conversation
Data and codes for ACL 2021 paper: Towards Emotional Support Dialog Systems
thu-coai/PsyQA
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/SafetyBench
Official github repo for SafetyBench, a comprehensive benchmark to evaluate LLMs' safety. [ACL 2024]
thu-coai/ShieldLM
ShieldLM: Empowering LLMs as Aligned, Customizable and Explainable Safety Detectors [EMNLP 2024 Findings]
thu-coai/CritiqueLLM
thu-coai/DA-Transformer
Official Implementation for the ICML2022 paper "Directed Acyclic Transformer for Non-Autoregressive Machine Translation"
thu-coai/PICL
Code for ACL2023 paper: Pre-Training to Learn in Context
thu-coai/ComplexBench
thu-coai/OpenMEVA
Benchmark for evaluating open-ended generation
thu-coai/AutoDetect
Official github repo for AutoDetect, an automated weakness detection framework for LLMs.
thu-coai/SafeUnlearning
Safe Unlearning: A Surprisingly Effective and Generalizable Solution to Defend Against Jailbreak Attacks
thu-coai/MiniPLM
thu-coai/MoralStory
thu-coai/JailbreakDefense_GoalPriority
[ACL 2024] Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization
thu-coai/AutoCAD
Official Code for EMNLP 2022 findings paper: "AutoCAD: Automatically Generating Counterfactuals for Mitigating Shortcut Learning"
thu-coai/Implicit-Toxicity
Official Code for EMNLP 2023 paper: "Unveiling the Implicit Toxicity in Large Language Models""
thu-coai/UDIT
Official Code for EMNLP2022 Paper: "Learning Instructions with Unlabeled Data for Zero-Shot Cross-Task Generalization"
thu-coai/DAG-Search
The beamsearch algorithm for DA-Transformer
thu-coai/MoralDial
The official Implementations of the paper: MoralDial: A Framework to Train and Evaluate Moral Dialogue Systems via Moral Discussions
thu-coai/Re3Dial
Official Code for EMNLP 2023 paper: "Re3Dial: Retrieve, Reorganize and Rescale Conversations for Long-Turn Open-Domain Dialogue Pre-training"
thu-coai/ERIC
Code for the AAAI 2023 paper "Generating Coherent Narratives by Learning Dynamic and Discrete Entity States with a Contrastive Framework"
thu-coai/SelfCont
Code for the paper "Mitigating the Learning Bias towards Repetition by Self-Contrastive Training for Open-Ended Generation"
thu-coai/CodePlan
thu-coai/ChatGLM6Bpkg
ChatGLM-6B: An Open Bilingual Dialogue Language Model | 开源双语对话语言模型
thu-coai/SPaR