 ChiQA: A Large Scale Image-based Real-World Question Answering Dataset
for Multi-Modal UnderstandingInternational Conference on Information and Knowledge Management (CIKM), 2022 |
 Catch Me If You Can: Deceiving Stance Detection and Geotagging Models to
Protect Privacy of Individuals on TwitterInternational Conference on Web and Social Media (ICWSM), 2022 |
 SoK: Content Moderation in Social Media, from Guidelines to Enforcement,
and Research to PracticeEuropean Symposium on Security and Privacy (Euro S&P), 2022 |
 Is Multi-Modal Necessarily Better? Robustness Evaluation of Multi-modal
Fake News DetectionIEEE Transactions on Network Science and Engineering (IEEE T-NSE), 2022 |
 Improving the Adversarial Robustness of NLP Models by Information
BottleneckFindings (Findings), 2022 |
 BITE: Textual Backdoor Attacks with Iterative Trigger InjectionAnnual Meeting of the Association for Computational Linguistics (ACL), 2022 |
 Does Your Model Classify Entities Reasonably? Diagnosing and Mitigating
Spurious Correlations in Entity TypingConference on Empirical Methods in Natural Language Processing (EMNLP), 2022 |
 Less Learn Shortcut: Analyzing and Mitigating Learning of Spurious
Feature-Label CorrelationInternational Joint Conference on Artificial Intelligence (IJCAI), 2022 |
 Teaching Broad Reasoning Skills for Multi-Step QA by Generating Hard
ContextsConference on Empirical Methods in Natural Language Processing (EMNLP), 2022 |
 Certified Robustness Against Natural Language Attacks by Causal
InterventionInternational Conference on Machine Learning (ICML), 2022 |
 Partial-input baselines show that NLI models can ignore context, but
they don'tNorth American Chapter of the Association for Computational Linguistics (NAACL), 2022 |
 Learning to Ignore Adversarial AttacksConference of the European Chapter of the Association for Computational Linguistics (EACL), 2022 |
 A Fine-grained Interpretability Evaluation Benchmark for Neural NLPConference on Computational Natural Language Learning (CoNLL), 2022 |
 A Word is Worth A Thousand Dollars: Adversarial Attack on Tweets Fools
Stock PredictionsNorth American Chapter of the Association for Computational Linguistics (NAACL), 2022 |
 Software Testing for Machine LearningAAAI Conference on Artificial Intelligence (AAAI), 2020 |
 Detecting Textual Adversarial Examples Based on Distributional
Characteristics of Data RepresentationsWorkshop on Representation Learning for NLP (RepL4NLP), 2022 |
 Can Rationalization Improve Robustness?North American Chapter of the Association for Computational Linguistics (NAACL), 2022 |
 Human-AI Collaboration via Conditional Delegation: A Case Study of
Content ModerationInternational Conference on Human Factors in Computing Systems (CHI), 2022 |
 Residue-Based Natural Language Adversarial Attack DetectionNorth American Chapter of the Association for Computational Linguistics (NAACL), 2022 |
 Logical Inference for Counting on Semi-structured TablesAnnual Meeting of the Association for Computational Linguistics (ACL), 2022 |
 Fast Few-shot Debugging for NLU Test SuitesWorkshop on Knowledge Extraction and Integration for Deep Learning Architectures; Deep Learning Inside Out (DeeLIO), 2022 |
 ASQA: Factoid Questions Meet Long-Form AnswersConference on Empirical Methods in Natural Language Processing (EMNLP), 2022 |
 Extending the Scope of Out-of-Domain: Examining QA models in multiple
subdomainsFirst Workshop on Insights from Negative Results in NLP (IFNRN), 2022 |
 VALUE: Understanding Dialect Disparity in NLUAnnual Meeting of the Association for Computational Linguistics (ACL), 2022 |
 A Rationale-Centric Framework for Human-in-the-loop Machine LearningAnnual Meeting of the Association for Computational Linguistics (ACL), 2022 |
 Feeding What You Need by Understanding What You LearnedAnnual Meeting of the Association for Computational Linguistics (ACL), 2022 |
 Synthetic Disinformation Attacks on Automated Fact Verification SystemsAAAI Conference on Artificial Intelligence (AAAI), 2022 |
