NLPExplorer

Kai Wei Chang

Number of Papers:- 158

Number of Citations:- 134

First ACL Paper:- 2009

Latest ACL Paper:- 2024

Venues:-

NAACL

CoNLL

TrustNLP

BEA

EMNLP

Findings

LREC

Rep4NLP

TACL

ACL

EACL

IJCNLP

AACL

Co-Authors:-

Abhilasha Ravichander

Adam Kalai

Ahmed Elgohary

Ahmed Hassan Awadallah

Akihiro Nishi

Similar Authors:-

BELIEVE: Belief-Enhanced Instruction Generation and Augmentation for Zero-Shot Bias Mitigation TrustNLP WS

Understanding and Mitigating Spurious Correlations in Text Classification with Neighborhood Analysis F i n d i n g s - E A C L

Oscar Chew | Hsuan-Tien Lin | Kai-Wei Chang | Kuan-Hao Huang |

Red Teaming Language Model Detectors with Language Models TACL

Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 3: System Demonstrations) NAACL

Kai-Wei Chang | Annie Lee | Nazneen Rajani |

Tokenization Matters: Navigating Data-Scarce Tokenization for Gender Inclusive Language Technologies F i n d i n g s - N A A C L

Proceedings of the 4th Workshop on Trustworthy Natural Language Processing (TrustNLP 2024) TrustNLP WS

Are LLMs Capable of Data-based Statistical and Causal Reasoning? Benchmarking Advanced Quantitative Reasoning with Data F i n d i n g s - A C L

Codec-SUPERB: An In-Depth Analysis of Sound Codec Models F i n d i n g s - A C L

KPEval: Towards Fine-Grained Semantic-Based Keyphrase Evaluation F i n d i n g s - A C L

Di Wu | Da Yin | Kai-Wei Chang |

Event Detection from Social Media for Epidemic Prediction NAACL

Agent Lumos: Unified and Modular Training for Open-Source Language Agents ACL

Tree-of-Traversals: A Zero-Shot Reasoning Algorithm for Augmenting Black-box Language Models with Knowledge Graphs ACL

Mitigating Bias for Question Answering Models by Tracking Bias Influence NAACL

The steerability of large language models toward data-driven personas NAACL

CASA: Causality-driven Argument Sufficiency Assessment NAACL

Xiao Liu | Yansong Feng | Kai-Wei Chang |

Contextual Label Projection for Cross-Lingual Structured Prediction NAACL

TextEE: Benchmark, Reevaluation, Reflections, and Future Challenges in Event Extraction F i n d i n g s - A C L

FLIRT: Feedback Loop In-context Red Teaming EMNLP

LLM-A*: Large Language Model Enhanced Incremental Heuristic Search on Path Planning F i n d i n g s - E M N L P

Model Editing Harms General Abilities of Large Language Models: Regularization to the Rescue EMNLP

MACAROON: Training Vision-Language Models To Be Your Engaged Partners F i n d i n g s - E M N L P

MetaKP: On-Demand Keyphrase Generation F i n d i n g s - E M N L P

Di Wu | Xiaoxian Shen | Kai-Wei Chang |

Control Large Language Models via Divide and Conquer EMNLP

VDebugger: Harnessing Execution Feedback for Debugging Visual Programs F i n d i n g s - E M N L P

Attribute Controlled Fine-tuning for Large Language Models: A Case Study on Detoxification F i n d i n g s - E M N L P

Synchronous Faithfulness Monitoring for Trustworthy Retrieval-Augmented Generation EMNLP

The Factuality Tax of Diversity-Intervened Text-to-Image Generation: Benchmark and Fact-Augmented Intervention EMNLP

Yixin Wan | Di Wu | Haoran Wang | Kai-Wei Chang |

QUDSELECT: Selective Decoding for Questions Under Discussion Parsing EMNLP

Re-ReST: Reflection-Reinforced Self-Training for Language Agents EMNLP

Data Advisor: Dynamic Data Curation for Safety Alignment of Large Language Models EMNLP

SPEED++: A Multilingual Event Extraction Framework for Epidemic Prediction and Preparedness EMNLP

Retrieval Enhanced Data Augmentation for Question Answering on Privacy Policies EACL

Summarize and Generate to Back-translate: Unsupervised Translation of Programming Languages EACL

Wasi Uddin Ahmad | Saikat Chakraborty | Baishakhi Ray | Kai-wei Chang |

Does BERT Exacerbate Gender or L1 Biases in Automated English Speaking Assessment? BEA

Symbolic Chain-of-Thought Distillation: Small Models Can Also “Think” Step-by-Step ACL

Dynosaur: A Dynamic Growth Paradigm for Instruction-Tuning Data Curation EMNLP

Are Personalized Stochastic Parrots More Dangerous? Evaluating Persona Biases in Dialogue Systems F i n d i n g s - E M N L P

What’s “up” with vision-language models? Investigating their struggle with spatial reasoning EMNLP

Amita Kamath | Jack Hessel | Kai-Wei Chang |

Rethinking Model Selection and Decoding for Keyphrase Generation with Pre-trained Sequence-to-Sequence Models EMNLP

Di Wu | Wasi Ahmad | Kai-Wei Chang |

Indirectly Supervised Natural Language Processing ACL

Dataset Bias Mitigation in Multiple-Choice Visual Question Answering and Beyond F i n d i n g s - E M N L P

IdealGPT: Iteratively Decomposing Vision and Language Reasoning via Large Language Models F i n d i n g s - E M N L P

Text encoders bottleneck compositionality in contrastive vision-language models EMNLP

Amita Kamath | Jack Hessel | Kai-Wei Chang |

“Kelly is a Warm Person, Joseph is a Role Model”: Gender Biases in LLM-Generated Reference Letters F i n d i n g s - E M N L P

PIP: Parse-Instructed Prefix for Syntactically Controlled Paraphrase Generation F i n d i n g s - A C L

Yixin Wan | Kuan-Hao Huang | Kai-Wei Chang |

ParaAMR: A Large-Scale Syntactically Diverse Paraphrase Dataset by AMR Back-Translation ACL

UniFine: A Unified and Fine-grained Approach for Zero-shot Vision-Language Understanding F i n d i n g s - A C L

AVATAR: A Parallel Corpus for Java-Python Program Translation F i n d i n g s - A C L

Wasi Uddin Ahmad | Md Golam Rahman Tushar | Saikat Chakraborty | Kai-Wei Chang |

Enhancing Unsupervised Semantic Parsing with Distributed Contextual Representations F i n d i n g s - A C L

LACMA: Language-Aligning Contrastive Learning with Meta-Actions for Embodied Instruction Following EMNLP

Self-Augmentation Improves Zero-Shot Cross-Lingual Transfer IJCNLP AACL

Fei Wang | Kuan-Hao Huang | Kai-Wei Chang | Muhao Chen |

PLUE: Language Understanding Evaluation Benchmark for Privacy Policies in English ACL

Jianfeng Chi | Wasi Uddin Ahmad | Yuan Tian | Kai-Wei Chang |

GENEVA: Benchmarking Generalizability for Event Argument Extraction with Hundreds of Event Types and Argument Roles ACL

Active Instruction Tuning: Improving Cross-Task Generalization by Training on Prompt Sensitive Tasks EMNLP

MetaVL: Transferring In-Context Learning Ability From Language Models to Vision-Language Models ACL

A Survey of Deep Learning for Mathematical Reasoning ACL

Resolving Ambiguities in Text-to-Image Generative Models ACL

The Tail Wagging the Dog: Dataset Construction Biases of Social Bias Benchmarks ACL

TAGPRIME: A Unified Framework for Relational Structure Extraction ACL

Efficient Shapley Values Estimation by Amortization for Text Classification ACL

Mitigating Gender Bias in Distilled Language Models via Counterfactual Role Reversal ACL Findings

On the Sensitivity and Stability of Model Interpretations in NLP ACL

Fan Yin | Zhouxing Shi | Cho-Jui Hsieh | Kai-Wei Chang |

Multilingual Generative Language Models for Zero-Shot Cross-Lingual Event Argument Extraction ACL

On the Intrinsic and Extrinsic Fairness Evaluation Metrics for Contextualized Language Representations ACL

Improving the Adversarial Robustness of NLP Models by Information Bottleneck ACL Findings

Towards Adversarially Robust Text Classifiers by Learning to Reweight Clean Examples ACL Findings

Measuring Fairness of Text Classifiers via Prediction Sensitivity ACL

Proceedings of the 2nd Workshop on Trustworthy Natural Language Processing (TrustNLP 2022) NAACL TrustNLP

DEGREE: A Data-Efficient Generation-Based Event Extraction Model NAACL

Socially Aware Bias Measurements for Hindi Language Representations NAACL

Using Item Response Theory to Measure Gender and Racial Bias of a BERT-based Automated English Speech Assessment System BEA NAACL

On Measures of Biases and Harms in NLP F i n d i n g s - A A C L

Empowering Language Models with Knowledge Graph Reasoning for Open-Domain Question Answering EMNLP

Weight Perturbation as Defense against Adversarial Word Substitutions F i n d i n g s - E M N L P

Representation Learning for Resource-Constrained Keyphrase Generation F i n d i n g s - E M N L P

Di Wu | Wasi Ahmad | Sunipa Dev | Kai-Wei Chang |

Find Someone Who: Visual Commonsense Understanding in Human-Centric Grounding F i n d i n g s - E M N L P

Conditional Supervised Contrastive Learning for Fair Text Classification F i n d i n g s - E M N L P

ADDMU: Detection of Far-Boundary Adversarial Examples with Data and Model Uncertainty Estimation EMNLP

Fan Yin | Yao Li | Cho-Jui Hsieh | Kai-Wei Chang |

How well can Text-to-Image Generative Models understand Ethical Natural Language Interventions? EMNLP

Hritik Bansal | Da Yin | Masoud Monajatipoor | Kai-Wei Chang |

Understanding ME? Multimodal Evaluation for Fine-grained Visual Commonsense EMNLP

Investigating Ensemble Methods for Model Robustness Improvement of Text Classifiers F i n d i n g s - E M N L P

Unsupervised Syntactically Controlled Paraphrase Generation with Abstract Meaning Representations F i n d i n g s - E M N L P

GeoMLAMA: Geo-Diverse Commonsense Probing on Multilingual Pre-Trained Language Models EMNLP

Generating Syntactically Controlled Paraphrases without Using Annotated Parallel Pairs EACL

Kuan-Hao Huang | Kai-Wei Chang |

Double Perturbation: On the Robustness of Robustness and Counterfactual Bias Evaluation NAACL

Disentangling Semantics and Syntax in Sentence Embeddings with Pre-trained Language Models NAACL

James Y. Huang | Kuan-Hao Huang | Kai-Wei Chang |

Adapting Coreference Resolution for Processing Violent Death Narratives NAACL

Evaluating the Values of Sources in Transfer Learning NAACL

Md Rizwan Parvez | Kai-Wei Chang |

“Nice Try, Kiddo”: Investigating Ad Hominems in Dialogue Responses NAACL

Emily Sheng | Kai-Wei Chang | Prem Natarajan | Nanyun Peng |

Unified Pre-training for Program Understanding and Generation NAACL

Wasi Ahmad | Saikat Chakraborty | Baishakhi Ray | Kai-Wei Chang |

Unsupervised Vision-and-Language Pre-training Without Parallel Images and Captions NAACL

Proceedings of the First Workshop on Trustworthy Natural Language Processing NAACL TrustNLP

Intent Classification and Slot Filling for Privacy Policies ACL IJCNLP

Societal Biases in Language Generation: Progress and Challenges ACL IJCNLP

Emily Sheng | Kai-Wei Chang | Prem Natarajan | Nanyun Peng |

Select, Extract and Generate: Neural Keyphrase Generation with Layer-wise Coverage Attention ACL IJCNLP

Wasi Ahmad | Xiao Bai | Soomin Lee | Kai-Wei Chang |

Searching for an Effective Defender: Benchmarking Defense against Adversarial Word Substitution EMNLP

Relation-Guided Pre-Training for Open-Domain Question Answering EMNLP Findings

Ziniu Hu | Yizhou Sun | Kai-Wei Chang |

Robustness and Adversarial Examples in Natural Language Processing EMNLP

Kai-Wei Chang | He He | Robin Jia | Sameer Singh |

Harms of Gender Exclusivity and Challenges in Non-Binary Representation in Language Technologies EMNLP

Defense against Synonym Substitution-based Adversarial Attacks via Dirichlet Neighborhood Ensemble ACL IJCNLP

On the Transferability of Adversarial Attacks against Neural Text Classifier EMNLP

Syntax-augmented Multilingual BERT for Cross-lingual Transfer ACL IJCNLP

Wasi Ahmad | Haoran Li | Kai-Wei Chang | Yashar Mehdad |

Improving Zero-Shot Cross-Lingual Transfer Learning via Robust Training EMNLP

Kuan-Hao Huang | Wasi Ahmad | Nanyun Peng | Kai-Wei Chang |

Broaden the Vision: Geo-Diverse Visual Commonsense Reasoning EMNLP

Retrieval Augmented Code Generation and Summarization EMNLP Findings

Does Robustness Improve Fairness? Approaching Fairness with Word Substitution Robustness Methods for Text Classification Findings