There are no reviews yet. Be the first to send feedback to the community and the maintainers!
CDial-GPT
A Large-scale Chinese Short-Text Conversation Dataset and Chinese pre-training dialog modelsSafety-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。CrossWOZ
A Large-Scale Chinese Cross-Domain Task-Oriented Dialogue DatasetKdConv
KdConv: A Chinese Multi-domain Dialogue Dataset Towards Multi-turn Knowledge-driven ConversationConvLab-2
ConvLab-2: An Open-Source Toolkit for Building, Evaluating, and Diagnosing Dialogue SystemsCharacterGLM-6B
CharacterGLM: Customizing Chinese Conversational AI Characters with Large Language ModelsEVA
EVA: Large-scale Pre-trained Chit-Chat ModelsBPO
Emotional-Support-Conversation
Data and codes for ACL 2021 paper: Towards Emotional Support Dialog Systemsccm
This project is a tensorflow implement of our work, CCM (Commonsense Conversational Model).ecm
This project is a tensorflow implement of our work, ECM (emotional chatting machine).NLG_book
书籍《现代自然语言生成》介绍COLDataset
The official repository of the paper: COLD: A Benchmark for Chinese Offensive Language DetectionPaperForONLG
Paper list for open-ended language generationPsyQA
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。SafetyBench
Official github repo for SafetyBench, a comprehensive benchmark to evaluate LLMs' safety.ShieldLM
ShieldLM: Empowering LLMs as Aligned, Customizable and Explainable Safety Detectorscotk
Conversational Toolkit. An Open-Source Toolkit for Fast Development and Fair Evaluation of Text GenerationDA-Transformer
Official Implementation for the ICML2022 paper "Directed Acyclic Transformer for Non-Autoregressive Machine Translation"PPT
Official Code for "PPT: Pre-trained Prompt Tuning for Few-shot Learning". ACL 2022CommonsenseStoryGen
Implementation for paper "A Knowledge-Enhanced Pretraining Model for Commonsense Story Generation"PICL
Code for ACL2023 paper: Pre-Training to Learn in ContextCritiqueLLM
tatk
Task-oriented dialog system toolkitsSentiLARE
Codes for our paper "SentiLARE: Sentiment-Aware Language Representation Learning with Linguistic Knowledge" (EMNLP 2020)THUOOP
清华大学面向对象程序设计课程 课程材料及答疑OPD
OPD: Chinese Open-Domain Pre-trained Dialogue ModelLOT-LongLM
JointGT
Codes for our paper "JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge Graphs" (ACL 2021 Findings)UNION
UNION: An Unreferenced Metric for Evaluating Open-ended Story GenerationOpenMEVA
Benchmark for evaluating open-ended generationHINT
CTRLEval
Codes for our paper "CTRLEval: An Unsupervised Reference-Free Metric for Evaluating Controlled Text Generation" (ACL 2022)CPT4DST
Official code for "Continual Prompt Tuning for Dialog State Tracking" (ACL 2022).seq2seq-pytorch-bert
DiaSafety
This repo is for the paper: On the Safety of Conversational Models: Taxonomy, Dataset, and BenchmarkTargeted-Data-Extraction
Official Code for ACL 2023 paper: "Ethicist: Targeted Training Data Extraction Through Loss Smoothed Soft Prompting and Calibrated Confidence Estimation"TaiLr
ICLR2023 - Tailoring Language Generation Models under Total Variation DistanceSafeUnlearning
Safe Unlearning: A Surprisingly Effective and Generalizable Solution to Defend Against Jailbreak AttacksLAUG
Language Understanding Augmentation Toolkit for Robustness TestingMoralStory
ConPer
Official Code for NAACL 2022 paper: "Persona-Guided Planning for Controlling the Protagonist's Persona in Story Generation"AugESC
Official repository for the Findings of ACL 2023 paper "AugESC: Dialogue Augmentation with Large Language Models for Emotional Support Conversation"NAST
Codes for "NAST: A Non-Autoregressive Generator with Word Alignment for Unsupervised Text Style Transfer" (ACL 2021 findings)CDConv
Data and codes for EMNLP 2022 paper "CDConv: A Benchmark for Contradiction Detection in Chinese Conversations"JailbreakDefense_GoalPriority
[ACL 2024] Defending Large Language Models Against Jailbreaking Attacks Through Goal PrioritizationAutoCAD
Official Code for EMNLP 2022 findings paper: "AutoCAD: Automatically Generating Counterfactuals for Mitigating Shortcut Learning"Implicit-Toxicity
Official Code for EMNLP 2023 paper: "Unveiling the Implicit Toxicity in Large Language Models""grounded-minimal-edit
Code for EMNLP 2021 paper "Transferable Persona-Grounded Dialogues via Grounded Minimal Edits"hred-tensorflow
EssayCommentGen
UDIT
Official Code for EMNLP2022 Paper: "Learning Instructions with Unlabeled Data for Zero-Shot Cross-Task Generalization"Reverse_Generation
earl
This project is a tensorflow implementation of our work, EARL.MoralDial
The official Implementations of the paper: MoralDial: A Framework to Train and Evaluate Moral Dialogue Systems via Moral DiscussionsseqGAN-tensorflow
LaMemo
NAACL2022 - LaMemo: Language Modeling with Look-Ahead MemoryRe3Dial
Official Code for EMNLP 2023 paper: "Re3Dial: Retrieve, Reorganize and Rescale Conversations for Long-Turn Open-Domain Dialogue Pre-training"ERIC
Code for the AAAI 2023 paper "Generating Coherent Narratives by Learning Dynamic and Discrete Entity States with a Contrastive Framework"DAG-Search
The beamsearch algorithm for DA-Transformercotk_docs
Document for cotk package. Refer to: https://github.com/thu-coai/cotklightseq-nat
A Modified Version of LightSeq for Non-Autoregressive Transformerseq2seq-pytorch
SelfCont
Code for the paper "Mitigating the Learning Bias towards Repetition by Self-Contrastive Training for Open-Ended Generation"CodePlan
transformerLM-pytorch
GPT2LM-pytorch
ConvLab-2_docs
CVAE-tensorflow
GRULM-pytorch
LM-tensorflow
cotk-test-CVAE
tatk_docs
The document of TaTK platform.seq2seq-tensorflow
VAE-tensorflow
ComplexBench
cotk_data
SST-pytorch
Love Open Source and this site? Check out how you can help us