Publications

Google Scholar profile (* denotes equal contribution)

2023

Beyond the Chat: Executable and Verifiable Text-Editing with LLMs
P Laban, J Vig, M Hearst, C Xiong, C Wu. Arxiv. [PDF]

Art or Artifice? Large Language Models and the False Promise of Creativity
T Chakrabarty, P Laban, D Agarwal, S Muresan, C Wu. Arxiv. [PDF]

Embrace Divergence for Richer Insights: A Multi-document Summarization Benchmark and a Case Study on Summarizing Diverse Information from News Articles
K Huang, P Laban, A Fabbri, P Choubey, S Joty, C Xiong, C Wu. Arxiv. [PDF]

Xgen-7b Technical Report
Salesforce AI Research. Arxiv. [PDF]

Next Steps for Human-Centered Generative AI: A Technical Perspective
X Chen, J Burke, R Du, M Hong, J Jacobs, P Laban, D Li, N Peng, K Willis, C Wu, B Zhou. Arxiv. [PDF]

SummEdits: Measuring LLM Ability at Factual Reasoning Through The Lens of Summarization
P Laban, W Kryściński, D Agarwal, A Fabbri, C Xiong, S Joty, C Wu. EMNLP 2023. [PDF]

Towards Interpretable and Efficient Automatic Reference-Based Summarization Evaluation
Y Liu, A Fabbri, Y Zhao, P Liu, S Joty, C Wu, C Xiong, D Radev. EMNLP 2023. [PDF]

INTELMO: Enhancing Models’ Adoption of Interactive Interfaces
C Yang, C Wu, L Murakhovs’ka, P Laban, X Chen. EMNLP 2023 (Demo). [PDF]

Salespeople vs SalesBot: Exploring the Role of Educational Value in Conversational Recommender Systems
L Murakhovs’ka, P Laban, T Xie, C Xiong, C Wu. EMNLP 2023 (Findings). [PDF]

Lexical Repetitions Lead to Rote Learning: Unveiling the Impact of Lexical Overlap in Train and Test Reference Summaries
P Choubey, A Fabri, C Xiong, C Wu. EMNLP 2023 (Findings). [PDF]

Did You Read the Instructions? Rethinking the Effectiveness of Task Definitions in Instruction Learning
F Yin, J Vig, P Laban, S Joty, C Xiong, C Wu. ACL 2023. [PDF]

SWiPE: A Dataset for Document-Level Simplification of Wikipedia Pages
P Laban, J Vig, W Kryscinski, S Joty, C Xiong, C Wu. ACL 2023. [PDF]

SOCRATIC Pretraining: Question-Driven Pretraining for Controllable Summarization
A Pagnoni, A Fabbri, W Kryscinski, C Wu. ACL 2023. [PDF]

Revisiting the Gold Standard: Grounding Summarization Evaluation with Robust Human Evaluation
Y Liu, A Fabbri, P Liu, Y Zhao, L Nan, R Han, S Han, S Joty, C Wu, C Xiong, D Radev. ACL 2023. [PDF]

CaPE: Contrastive Parameter Ensembling for Reducing Hallucination in Abstractive Summarization
P Choubey, A Fabbri, J Vig, C Wu, W Liu, N Rajani. ACL-Findings 2023. [PDF]

Designing and Evaluating Interfaces that Highlight News Coverage Diversity Using Discord Questions
P Laban, C Wu, L Murakhovs’ka, X Chen, C Xiong. CHI 2023. [PDF]

Model ensemble instead of prompt fusion: a sample-specific knowledge transfer method for few-shot prompt tuning
X Peng, C Xing, P Choubey, C Wu, C Xiong. ICLR 2023. [PDF]

2022

Near-Negative Distinction: Giving a Second Life to Human Evaluation Datasets
P Laban, C Wu, W Liu, C Xiong. EMNLP 2022. [PDF]

Improving Factual Consistency in Summarization with Compression-Based Post-Editing
A Fabbri, P Choubey, J Vig, C Wu, C Xiong. EMNLP 2022 (short). [PDF]

Discord Questions: A Computational Approach To Diversity Analysis in News Coverage.
P Laban, C Wu, L Murakhovs’ka, X Chen and C Xiong. EMNLP-Findings 2022. [PDF]

Conformal Predictor for Improving Zero-Shot Text Classification Efficiency
P Choubey, Y Bai, C Wu, W Liu and N Rajani. EMNLP 2022 (short). [PDF]

UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models
T Xie, C Wu, P Shi, R Zhong, T Scholak, M Yasunaga, C Wu, M Zhong, Pg Yin, S Wang, V Zhong, B Wang, C Li, C Boyle, A Ni, Z Yao, D Radev, C Xiong, L Kong, R Zhang, N Smith, L Zettlemoyer, T Yu. EMNLP 2022. [PDF] [Code]

QAFactEval: Improved QA-Based Factual Consistency Evaluation for Summarization
A Fabbri, C Wu, W Liu, C Xiong. NAACL 2022. [PDF] [Code]

Exploring Neural Models for Query-Focused Summarization
J Vig, A Fabbri, WKryściński, C Wu, W Liu. NAACL-Findings 2022. [PDF] [Code]

MixQG: Neural Question Generation with Mixed Answer Types
L Murakhovs’ka, C Wu, T Niu, W Liu, C Xiong. NAACL-Findings 2022 (Short). [PDF] [Code]

Quiz Design Task: Helping Teachers Create Quizzes with Automated Question Generation
P Laban, C Wu, L Murakhovs’ka, W Liu, C Xiong. NAACL-Findings 2022 (Short).

QAConv: Question Answering on Informative Conversations
C Wu, A Madotto, W Liu, P Fung, C Xiong. ACL 2022. [PDF] [Code] [Blog]

DialFact: A Benchmark for Fact-Checking in Dialogue
P Gupta, C Wu, W Liu, C Xiong. ACL 2022. [PDF] [Code]

Model Ensemble Instead of Prompt Fusion: A Sample-specific Knowledge Transfer Method for Few-shot Prompt Tuning
X Peng, C Xing, P Choubey, C Wu, C Xiong. Arxiv. [PDF]

Marvista: A Human-AI Collaborative Reading Tool
X Chen, C Wu, T Niu, W Liu, C Xiong. ACM-HCI. [PDF]

CaPE: Contrastive Parameter Ensembling for Reducing Hallucination in Abstractive Summarization
P Choubey, A Fabbri, J Vig, C Wu, We Liu, N Rajani. Arxiv. [PDF]

Structure Extraction in Task-Oriented Dialogues with Slot Clustering
L Qiu, C Wu, W Liu, C Xiong. Arxiv. [PDF] [Code]

2021

Controllable Abstractive Dialogue Summarization with Sketch Supervision
C Wu*, L Liu*, W Liu, P Stenetorp, C Xiong. ACL-Findings 2021. [PDF] [Code]

GraPPa: Grammar-Augmented Pre-Training for Table Semantic Parsing
T Yu, C Wu, X Lin, B Wang, Y Tan, X Yang, D Radev, R Socher, C Xiong. ICLR 2021. [PDF]

Robustness gym: Unifying the nlp evaluation landscape
K Goel, N Rajani, J Vig, S Tan, C Wu, S Zheng, C Xiong, M Bansal, C Ré. Arxiv. [PDF]

2020

ToD-BERT: Pre-trained Natural Language Understanding for Task-Oriented Dialogues
C Wu, S Hoi, R Socher, and C Xiong. EMNLP 2020. [PDF] [Code] [Slide]

Probing Task-Oriented Dialogue Representation from Language Models
C Wu and C Xiong. EMNLP 2020. [PDF]

DISCERN: Discourse-Aware Entailment Reasoning Network for Conversational Machine Reading
Y Gao, C Wu, J Li, S Joty, S Hoiu, C Xiong, I King, and M Lyu. EMNLP 2020. [PDF] [Code]

Discriminative Nearest Neighbor Few-Shot Intent Detection by Transferring Natural Language Inference
J Zhang, K Hashimoto, W Liu, C Wu, Y Wan, P Yu, R Socher and C Xiong. EMNLP 2020. [PDF]

Improving Limited Labeled Dialogue State Tracking with Self-Supervision
C Wu, S Hoi and C Xiong. EMNLP-findings 2020. [PDF] [PDF]

A Simple Language Model for Task-Oriented Dialogue
E Hosseini-Asl, B McCann, C Wu, S Yavuz, and R Socher. NeurIPS 2020 (Spotlight). [PDF] Code

Explicit Memory Tracker with Coarse-to-Fine Reasoning for Conversational Machine Reading
Y Gao, C Wu, S Joty, C Xiong, R Socher,I King, M Lyu, and S Hoi. ACL 2020. [PDF]

Getting To Know You: User Attribute Extraction from Dialog
C Wu, A Madotto, Z Lin, P Xu, P Fung. LREC, 2020 (Oral) . [PDF]

2019

Attention over Parameters for Dialogue Systems
A Madotto, Z Lin, C Wu, J Shin, P Fung. NeurIPS ConvAI Workshop, 2019 (Oral, Best Paper Award) [1 out of 30 accepted papers]. [PDF]

Code-switched language models using neural based synthetic data from parallel sentences
G Winata, A Madotto, C Wu, P Fung. CoNLL 2019. [PDF]

Clickbait? Sensational Headline Generation with Auto-tuned Reinforcement Learning
P Xu, C Wu, A Madotto, P Fung. EMNLP 2019. [PDF] [Code]

Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systems
C Wu, A Madotto, E Hosseini-Asl, C Xiong, R Socher, P Fung. ACL 2019 (Oral, Outstanding Paper Award) [top 1% accepted papers]. [PDF] [Code] [Slides] [Video]

Personalizing Dialogue Agents via Meta-Learning
A Madotto, Z Lin, C Wu, P Fung. ACL 2019 (short). [PDF] [Code]

Global-to-local Memory Pointer Networks for Task-Oriented Dialogue
C Wu, C Xiong, R Socher. NeurIPS Workshop on Conversational AI 2018 (Oral) and ICLR 2019. [PDF] [Slide] [Code]

Learning to Memorize in Neural Task-Oriented Dialogue Systems
C Wu. HKUST MPhil Thesis 2019.
[PDF] [Slides]

Code-switched language models using neural based synthetic data from parallel sentences
G Winata, A Madotto, C Wu, P Fung. ACL 2019. [PDF]

2018

Improving Large-Scale Fact-Checking using Decomposable Attention Models and Lexical Tagging
C Wu*, N Lee*, P Fung. EMNLP 2018 (short). [PDF] [Poster]

Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Oriented Dialog Systems
C Wu*, A Madotto*, P Fung. ACL 2018. [PDF] [Poster] [Code]

Empathetic Dialog Systems
P Fung, D Bertero, P Xu, J Park, C Wu, A Madotto. LREC 2018. [PDF]

End-to-End Dynamic Query Memory Network for Entity-Value Independent Task-oriented Dialog
C Wu, A Madotto, G Winata, P Fung. ICASSP 2018. [PDF]

Emo2Vec: Learning Generalized Emotion Representation by Multi-task Training
P Xu, A Madotto, C Wu, J Park, P Fung. EMNLP Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis, 2018. [PDF]

Bilingual Character Representation for Efficiently Addressing Out-of-Vocabulary Words in Code-Switching Named Entity Recognition
G Winata, C Wu, A Madotto, P Fung. ACL Code-Switching Workshop, 2018. [PDF]

Code-Switching Language Modeling using Syntax-Aware Multi-Task Learning
G Winata, A Madotto, C Wu, P Fung. ACL Code-Switching Workshop, 2018. [PDF]

End-to-end Automatic Code-Switching Speech Recognition
G Winata, A Madotto, C Wu, P Fung. [PDF]

- 2017

End-to-End Recurrent Entity Network for Entity-Value Independent Goal-Oriented Dialog Learning
C Wu*, A Madotto*, G Winata, P Fung. DSTC6. [PDF] [Code]

Zara: A Virtual Interactive Dialogue System Incorporating Emotion, Sentiment and Personality Recognition
P Fung, A Dey, F Siddique, R Lin, Y Yang, D Bertero, W Yan, R Yin, C Wu. COLING Demo 2016. [PDF]

Real-Time Speech Emotion and Sentiment Recognition for Interactive Dialogue Systems
D Bertero, F Siddique, C Wu, Y Wan, R Chan and P Fung. EMNLP 2016 (short). [PDF]

Towards Empathetic Human-Robot Interactions
P Fung, D Bertero, Y Wan, A Dey, R Chan, F Siddique, Y Yang, C Wu, R Lin. CICLing 2016. [PDF]

Simulations for Time-Optimal Trajectory Planning along Parametric Polynomial Lane-Change Curves for a Unicycle
C Wu, ZY Chiu, JS Liu. IEEE ROBIO 2017. [PDF]

JointRF/Baseband Grouping-based Codebook Design for Hybrid Beamforming in mmWave MIMO Systems
C Wu, CH Chen, CR Tsai, and AY Wu. ICSPCC 2016. [PDF]