b'Maosong Sun'

research

∙ 09/19/2023

QASnowball: An Iterative Bootstrapping Framework for High-Quality Question-Answering Data Generation

Recent years have witnessed the success of question answering (QA), espe...

0 Kunlun Zhu, et al. ∙

research

∙ 09/15/2023

Empowering Private Tutoring by Chaining Large Language Models

Artificial intelligence has been applied in various aspects of online ed...

0 Yulin Chen, et al. ∙

research

∙ 08/24/2023

Large Language Model as Autonomous Decision Maker

While large language models (LLMs) exhibit impressive language understan...

0 Yining Ye, et al. ∙

research

∙ 08/21/2023

AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors in Agents

Autonomous agents empowered by Large Language Models (LLMs) have undergo...

0 Weize Chen, et al. ∙

research

∙ 07/31/2023

ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs

Despite the advancements of open-source large language models (LLMs) and...

0 Yujia Qin, et al. ∙

research

∙ 07/28/2023

Exploring Format Consistency for Instruction Tuning

Instruction tuning has emerged as a promising approach to enhancing larg...

0 Shihao Liang, et al. ∙

research

∙ 07/16/2023

Communicative Agents for Software Development

Software engineering is a domain characterized by intricate decision-mak...

0 Chen Qian, et al. ∙

research

∙ 07/15/2023

CPET: Effective Parameter-Efficient Tuning for Compressed Large Language Models

Parameter-efficient tuning (PET) has been widely explored in recent year...

0 Weilin Zhao, et al. ∙

research

∙ 07/05/2023

OpenDelta: A Plug-and-play Library for Parameter-efficient Adaptation of Pre-trained Models

The scale of large pre-trained models (PTMs) poses significant challenge...

0 Shengding Hu, et al. ∙

research

∙ 07/05/2023

Won't Get Fooled Again: Answering Questions with False Premises

Pre-trained language models (PLMs) have shown unprecedented potential in...

0 Shengding Hu, et al. ∙

research

∙ 06/21/2023

Interactive Molecular Discovery with Natural Language

Natural language is expected to be a key medium for various human-machin...

0 Zheni Zeng, et al. ∙

research

∙ 06/07/2023

Revisiting Out-of-distribution Robustness in NLP: Benchmark, Analysis, and LLMs Evaluations

This paper reexamines the research on out-of-distribution (OOD) robustne...

0 Lifan Yuan, et al. ∙

research

∙ 06/04/2023

Arbitrary Few Parameters are Good Enough for Adapting Large-scale Pre-trained Language Models

Parameter-efficient tuning (PET) methods can effectively drive extremely...

2 Yusheng Su, et al. ∙

research

∙ 05/29/2023

From Adversarial Arms Race to Model-centric Evaluation: Motivating a Unified Automatic Robustness Evaluation Framework

Textual adversarial attacks can discover models' weaknesses by adding se...

0 Yangyi Chen, et al. ∙

research

∙ 05/28/2023

Emergent Modularity in Pre-trained Transformers

This work examines the presence of modularity in pre-trained Transformer...

0 Zhengyan Zhang, et al. ∙

research

∙ 05/28/2023

Plug-and-Play Knowledge Injection for Pre-trained Language Models

Injecting external knowledge can improve the performance of pre-trained ...

0 Zhengyan Zhang, et al. ∙

research

∙ 05/28/2023

Stochastic Bridges as Effective Regularizers for Parameter-Efficient Tuning

Parameter-efficient tuning methods (PETs) have achieved promising result...

0 Weize Chen, et al. ∙

research

∙ 05/28/2023

Plug-and-Play Document Modules for Pre-trained Models

Large-scale pre-trained models (PTMs) have been widely used in document-...

0 Chaojun Xiao, et al. ∙

research

∙ 05/23/2023

Enhancing Chat Language Models by Scaling High-quality Instructional Conversations

Fine-tuning on instruction data has been widely validated as an effectiv...

0 Ning Ding, et al. ∙

research

∙ 05/19/2023

Efficient Cross-Lingual Transfer for Chinese Stable Diffusion with Images as Pivots

Diffusion models have made impressive progress in text-to-image synthesi...

0 Jinyi Hu, et al. ∙

research

∙ 05/15/2023

Recyclable Tuning for Continual Pre-training

Continual pre-training is the paradigm where pre-trained language models...

0 Yujia Qin, et al. ∙

research

∙ 05/15/2023

C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models

New NLP benchmarks are urgently needed to align with the rapid developme...

0 Yuzhen Huang, et al. ∙

research

∙ 05/11/2023

WebCPM: Interactive Web Search for Chinese Long-form Question Answering

Long-form question answering (LFQA) aims at answering complex, open-ende...

0 Yujia Qin, et al. ∙

research

∙ 05/02/2023

UNTER: A Unified Knowledge Interface for Enhancing Pre-trained Language Models

Recent research demonstrates that external knowledge injection can advan...

0 Deming Ye, et al. ∙

research

∙ 04/21/2023

CLaMP: Contrastive Language-Music Pre-training for Cross-Modal Symbolic Music Information Retrieval

We introduce CLaMP: Contrastive Language-Music Pre-training, which learn...

0 Shangda Wu, et al. ∙

research

∙ 04/17/2023

Tool Learning with Foundation Models

Humans possess an extraordinary ability to create and utilize tools, all...

1 Yujia Qin, et al. ∙

research

∙ 02/14/2023

READIN: A Chinese Multi-Task Benchmark with Realistic and Diverse Input Noises

For many real-world applications, the user-generated inputs usually cont...

0 Chenglei Si, et al. ∙

research

∙ 01/07/2023

TunesFormer: Forming Tunes with Control Codes

In recent years, deep learning techniques have been applied to music gen...

0 Shangda Wu, et al. ∙

research

∙ 12/16/2022

Decoder Tuning: Efficient Language Understanding as Decoding

With the evergrowing sizes of pre-trained models (PTMs), it has been an ...

0 Ganqu Cui, et al. ∙

research

∙ 11/22/2022

Visually Grounded Commonsense Knowledge Acquisition

Large-scale commonsense knowledge bases empower a broad range of AI appl...

0 Yuan Yao, et al. ∙

research

∙ 11/21/2022

Exploring the Efficacy of Pre-trained Checkpoints in Text-to-Music Generation Task

Benefiting from large-scale datasets and pre-trained models, the field o...

0 Shangda Wu, et al. ∙

research

∙ 11/14/2022

Evade the Trap of Mediocrity: Promoting Diversity and Novelty in Text Generation via Concentrating Attention

Recently, powerful Transformer architectures have proven superior in gen...

0 Wenhao Li, et al. ∙

research

∙ 10/25/2022

Exploring Mode Connectivity for Pre-trained Language Models

Recent years have witnessed the prevalent application of pre-trained lan...

0 Yujia Qin, et al. ∙

research

∙ 10/24/2022

Different Tunes Played with Equal Skill: Exploring a Unified Optimization Subspace for Delta Tuning

Delta tuning (DET, also known as parameter-efficient tuning) is deemed a...

0 Jing Yi, et al. ∙

research

∙ 10/22/2022

Recurrence Boosts Diversity! Revisiting Recurrent Latent Variable in Transformer-Based Variational AutoEncoder for Diverse Text Generation

Variational Auto-Encoder (VAE) has been widely adopted in text generatio...

0 Jinyi Hu, et al. ∙

research

∙ 10/19/2022

Why Should Adversarial Perturbations be Imperceptible? Rethink the Research Paradigm in Adversarial NLP

Textual adversarial samples play important roles in multiple subfields o...

0 Yangyi Chen, et al. ∙

research

∙ 09/20/2022

Automatic Label Sequence Generation for Prompting Sequence-to-sequence Models

Prompting, which casts downstream applications as language modeling task...

1 Zichun Yu, et al. ∙

research

∙ 09/14/2022

CCOM-HuQin: an Annotated Multimodal Chinese Fiddle Performance Dataset

HuQin is a family of traditional Chinese bowed string instruments. Playi...

0 Yu Zhang, et al. ∙

research

∙ 07/13/2022

Fuse It More Deeply! A Variational Transformer with Layer-Wise Latent Variable Inference for Text Generation

The past several years have witnessed Variational Auto-Encoder's superio...

15 Jinyi Hu, et al. ∙

research

∙ 06/19/2022

A Unified Understanding of Deep NLP Models for Text Classification

The rapid development of deep natural language processing (NLP) models f...

0 Zhen Li, et al. ∙

research

∙ 06/17/2022

A Unified Evaluation of Textual Backdoor Learning: Frameworks and Benchmarks

Textual backdoor attacks are a kind of practical threat to NLP systems. ...

0 Ganqu Cui, et al. ∙

research

∙ 06/15/2022

Sparse Structure Search for Parameter-Efficient Tuning

Adapting large pre-trained models (PTMs) through fine-tuning imposes pro...

11 Shengding Hu, et al. ∙

research

∙ 05/23/2022

PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models

Vision-language pre-training (VLP) has shown impressive performance on a...

1 Yuan Yao, et al. ∙

research

∙ 05/23/2022

Prompt Tuning for Discriminative Pre-trained Language Models

Recent works have shown promising results of prompt tuning in stimulatin...

4 Yuan Yao, et al. ∙

research

∙ 05/12/2022

Sampling with Attribute-Related Information for Controlling Language Models

The dominant approaches for controlling language models are based on fin...

0 Shangda Wu, et al. ∙

research

∙ 03/22/2022

Fine-Grained Scene Graph Generation with Data Transfer

Scene graph generation (SGG) aims to extract (subject, predicate, object...

0 Ao Zhang, et al. ∙

research

∙ 03/16/2022

LEVEN: A Large-Scale Chinese Legal Event Detection Dataset

Recognizing facts is the most fundamental step in making judgments, henc...

0 Feng Yao, et al. ∙

research

∙ 03/14/2022

Sememe Prediction for BabelNet Synsets using Multilingual and Multimodal Information

In linguistics, a sememe is defined as the minimum semantic unit of lang...

0 Fanchao Qi, et al. ∙

research

∙ 03/12/2022

ELLE: Efficient Lifelong Pre-training for Emerging Data

Current pre-trained language models (PLM) are typically trained with sta...

6 Yujia Qin, et al. ∙

research

∙ 02/27/2022

A Simple but Effective Pluggable Entity Lookup Table for Pre-trained Language Models

Pre-trained language models (PLMs) cannot well recall rich factual knowl...

0 Deming Ye, et al. ∙

Maosong Sun

Featured Co-authors