Diyi Yang

Future of Work in the Age of LLMs ACL 2026 AudioJudge: Understanding What Works in Large Audio Model Based Speech Evaluation EACL 2026 Putting HUMANS first: Efficient LAM Evaluation with Human Preference Alignment ACL 2026 Design2Code: Benchmarking Multimodal Code Generation for Automated Front-End Engineering NAACL 2025 Sketch2Code: Evaluating Vision-Language Models for Interactive Web Design Prototyping NAACL 2025 Culture Cartography: Mapping the Landscape of Cultural Knowledge EMNLP 2025 SPHERE: An Evaluation Card for Human-AI Systems ACL 2025 Internal Causal Mechanisms Robustly Predict Language Model Out-of-Distribution Behaviors ICML 2025 EgoNormia: Benchmarking Physical-Social Norm Understanding ACL 2025 Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers ICLR 2025 EquiBench: Benchmarking Large Language Models’ Reasoning about Program Semantics via Equivalence Checking EMNLP 2025 Identifying Unlearned Data in LLMs via Membership Inference Attacks EMNLP 2025 Aligning Language Models with Demonstrated Feedback ICLR 2025 SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains? ICLR 2025 Human-AI Collaboration: How AIs Augment Human Teammates ACL 2025 Distilling an End-to-End Voice Assistant Without Instruction Training Data ACL 2025 SynthesizeMe! Inducing Persona-Guided Prompts for Personalized Reward Models in LLMs ACL 2025 Attacking Vision-Language Computer Agents via Pop-ups ACL 2025 Mind the Gap: Static and Interactive Evaluations of Large Audio Models ACL 2025 No Preference Left Behind: Group Distributional Preference Optimization ICLR 2025 Social Intelligence in the Age of LLMs NAACL 2025 How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs ACL 2024 Unintended Impacts of LLM Alignment on Global Representation ACL 2024 Simulated Misinformation Susceptibility (SMISTS): Enhancing Misinformation Research with Large Language Model Simulations ACL 2024 Social Intelligence Data Infrastructure: Structuring the Present and Navigating the Future ACL 2024 Measuring and Addressing Indexical Bias in Information Retrieval ACL 2024 Perceptions of Language Technology Failures from South Asian English Speakers ACL 2024 Position: A Safe Harbor for AI Evaluation and Red Teaming ICML 2024 Are Large Language Models Consistent over Value-laden Questions? EMNLP 2024 Anchor Points: Benchmarking Models with Much Fewer Examples EACL 2024 Modeling Gender and Dialect Bias in Automatic Speech Recognition EMNLP 2024 Benchmarking Machine Translation with Cultural Awareness EMNLP 2024 CultureBank: An Online Community-Driven Knowledge Base Towards Culturally Aware Language Technologies EMNLP 2024 Language Agents: Foundations, Prospects, and Risks EMNLP 2024 Decoding Susceptibility: Modeling Misbelief to Misinformation Through a Computational Approach EMNLP 2024 Demystifying Verbatim Memorization in Large Language Models EMNLP 2024 Roleplay-doh: Enabling Domain-Experts to Create LLM-simulated Patients via Eliciting and Adhering to Principles EMNLP 2024 DyVal: Dynamic Evaluation of Large Language Models for Reasoning Tasks ICLR 2024 Training Socially Aligned Language Models on Simulated Social Interactions ICLR 2024 PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Action NIPS 2024 Semi-Truths: A Large-Scale Dataset of AI-Augmented Images for Evaluating Robustness of AI-Generated Image detectors NIPS 2024 DARG: Dynamic Evaluation of Large Language Models via Adaptive Reasoning Graph NIPS 2024 MIDDAG: Where Does Our News Go? Investigating Information Diffusion via Community-Level Information Pathways AAAI 2024 Human-AI Interaction in the Age of LLMs NAACL 2024 Grounding Gaps in Language Model Generations NAACL 2024 Multi-Level Feedback Generation with Large Language Models for Empowering Novice Peer Counselors ACL 2024 Silent Signals, Loud Impact: LLMs for Word-Sense Disambiguation of Coded Dog Whistles ACL 2024 Parameter-Efficient Fine-Tuning Design Spaces ICLR 2023 Multi-VALUE: A Framework for Cross-Dialectal English NLP ACL 2023 Compositional Data Augmentation for Abstractive Conversation Summarization ACL 2023 DAMP: Doubly Aligned Multilingual Parser for Task-Oriented Dialogue ACL 2023 On Second Thought, Let’s Not Think Step by Step! Bias and Toxicity in Zero-Shot Reasoning ACL 2023 Forgotten Knowledge: Examining the Citational Amnesia in NLP ACL 2023 NormBank: A Knowledge Bank of Situational Social Norms ACL 2023 DynaMiTE: Discovering Explosive Topic Evolutions with User Guidance ACL 2023 TADA : Task Agnostic Dialect Adapters for English ACL 2023 Modeling Cross-Cultural Pragmatic Inference with Codenames Duet ACL 2023 Werewolf Among Us: Multimodal Resources for Modeling Persuasion Behaviors in Social Deduction Games ACL 2023 Controllable Conversation Generation with Conversation Structures via Diffusion Models ACL 2023 Human-in-the-loop Abstractive Dialogue Summarization ACL 2023 ConStruct-VL: Data-Free Continual Structured VL Concepts Learning CVPR 2023 Shapley Head Pruning: Identifying and Removing Interference in Multilingual Transformers EACL 2023 Summarization of Dialogues and Conversations At Scale EACL 2023 Bounding the Capabilities of Large Language Models in Open Text Generation with Prompt Constraints EACL 2023 Missing Information, Unresponsive Authors, Experimental Flaws: The Impossibility of Assessing the Reproducibility of Previous Human Evaluations in NLP EACL 2023 Is ChatGPT a General-Purpose Natural Language Processing Task Solver? EMNLP 2023 CoAnnotating: Uncertainty-Guided Work Allocation between Human and Large Language Models for Data Annotation EMNLP 2023 Generating and Evaluating Tests for K-12 Students with Language Model Simulations: A Case Study on Sentence Reading Efficiency EMNLP 2023 A Cheaper and Better Diffusion Language Model with Soft-Masked Noise EMNLP 2023 Task-Agnostic Low-Rank Adapters for Unseen English Dialects EMNLP 2023 “Mistakes Help Us Grow”: Facilitating and Evaluating Growth Mindset Supportive Language in Classrooms EMNLP 2023 CoMPosT: Characterizing and Evaluating Caricature in LLM Simulations EMNLP 2023 Deciphering Stereotypes in Pre-Trained Language Models EMNLP 2023 Unlearn What You Want to Forget: Efficient Unlearning for LLMs EMNLP 2023 Impressions: Visual Semiotics and Aesthetic Impact Understanding EMNLP 2023 DADA: Dialect Adaptation via Dynamic Aggregation of Linguistic Rules EMNLP 2023 Designing, Evaluating, and Learning from Humans Interacting with NLP Models EMNLP 2023 Mitigating Biases in Hate Speech Detection from A Causal Perspective EMNLP 2023 Culturally Aware Natural Language Inference EMNLP 2023 Automatic Reflection Generation for Peer-to-Peer Counseling EMNLP 2023 Focus on the Action: Learning to Highlight and Summarize Jointly for Email To-Do Items Summarization ACL 2022 Leveraging Expert Guided Adversarial Augmentation For Improving Generalization in Named Entity Recognition ACL 2022 GNN is a Counter? Revisiting GNN for Question Answering ICLR 2022 Learning with Limited Text Data ACL 2022 DMix: Adaptive Distance-aware Interpolative Mixup ACL 2022 Measure and Improve Robustness in NLP Models: A Survey NAACL 2022 TreeMix: Compositional Constituency-based Data Augmentation for Natural Language Understanding NAACL 2022 SUBS: Subtree Substitution for Compositional Semantic Parsing NAACL 2022 When FLUE Meets FLANG: Benchmarks and Large Pretrained Language Model for Financial Domain EMNLP 2022 Robustness of Demonstration-based Learning Under Limited Data Scenario EMNLP 2022 A Search Engine for Discovery of Scientific Challenges and Directions AAAI 2022 SEQZERO: Few-shot Compositional Semantic Parsing with Sequential Prompts and Zero-shot Models NAACL 2022 Geographic Citation Gaps in NLP Research EMNLP 2022 Explaining Toxic Text via Knowledge Enhanced Text Generation NAACL 2022 Fantastic Questions and Where to Find Them: FairytaleQA – An Authentic Dataset for Narrative Comprehension ACL 2022 Continual Sequence Generation with Adaptive Compositional Modules ACL 2022 Inducing Positive Perspectives with Text Reframing ACL 2022 VALUE: Understanding Dialect Disparity in NLU ACL 2022 The Moral Integrity Corpus: A Benchmark for Ethical Dialogue Systems ACL 2022 A Sketch Is Worth a Thousand Words: Image Retrieval with Text and Sketch ECCV 2022 Identifying and Mitigating Spurious Correlations for Improving Robustness in NLP Models NAACL 2022 DoubleMix: Simple Interpolation-Based Data Augmentation for Text Classification COLING 2022 To Protect and To Serve? Analyzing Entity-Centric Framing of Police Violence EMNLP 2021 Disfl-QA: A Benchmark Dataset for Understanding Disfluencies in Question Answering ACL 2021 HiddenCut: Simple Data Augmentation for Natural Language Understanding with Better Generalizability ACL 2021 Weakly-Supervised Hierarchical Models for Predicting Persuasive Strategies in Good-faith Textual Requests AAAI 2021 Putting Humans in the Natural Language Processing Loop: A Survey EACL 2021 The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics ACL 2021 Personalized Response Generation with Tensor Factorization ACL 2021 HiddenCut: Simple Data Augmentation for Natural Language Understanding with Better Generalizability IJCNLP 2021 Disfl-QA: A Benchmark Dataset for Understanding Disfluencies in Question Answering IJCNLP 2021 Personalized Response Generation with Tensor Factorization IJCNLP 2021 The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics IJCNLP 2021 The Importance of Modeling Social Factors of Language: Theory and Practice NAACL 2021 Structure-Aware Abstractive Conversation Summarization via Discourse and Action Graphs NAACL 2021 Personalized Response Generation via Generative Split Memory Network NAACL 2021 Latent Hatred: A Benchmark for Understanding Implicit Hate Speech EMNLP 2021 Frustratingly Simple but Surprisingly Strong: Using Language-Independent Features for Zero-shot Cross-lingual Semantic Parsing EMNLP 2021 Simple Conversational Data Augmentation for Semi-supervised Abstractive Dialogue Summarization EMNLP 2021 HypMix: Hyperbolic Interpolative Data Augmentation EMNLP 2021 WIKIBIAS: Detecting Multi-Span Subjective Biases in Language EMNLP 2021 Semantic Categorization of Social Knowledge for Commonsense Question Answering EMNLP 2021 Continual Learning for Text Classification with Information Disentanglement Based Regularization NAACL 2021 MixText: Linguistically-Informed Interpolation of Hidden Space for Semi-Supervised Text Classification ACL 2020 ToTTo: A Controlled Table-To-Text Generation Dataset EMNLP 2020 Planning and Generating Natural and Diverse Disfluent Texts as Augmentation for Disfluency Detection EMNLP 2020 Multi-View Sequence-to-Sequence Models with Conversational Structure for Abstractive Dialogue Summarization EMNLP 2020 Examining the Ordering of Rhetorical Strategies in Persuasive Requests EMNLP 2020 Semi-supervised Formality Style Transfer using Language Model Discriminator and Mutual Information Maximization EMNLP 2020 Automatically Neutralizing Subjective Bias in Text AAAI 2020 Local Additivity Based Data Augmentation for Semi-supervised NER EMNLP 2020 Let’s Make Your Request More Persuasive: Modeling Persuasive Strategies via Semi-Supervised Neural Nets on Crowdfunding Platforms NAACL 2019 Proceedings of the 2019 Workshop on Widening NLP ACL 2019 Identifying Semantic Edit Intentions from Revisions in Wikipedia EMNLP 2017 Hierarchical Attention Networks for Document Classification NAACL 2016 Weakly Supervised Role Identification in Teamwork Interactions IJCNLP 2015 Humor Recognition and Humor Anchor Extraction EMNLP 2015 That’s So Annoying!!!: A Lexical and Frame-Semantic Embedding Based Data Augmentation Approach to Automatic Categorization of Annoying Behaviors using #petpeeve Tweets EMNLP 2015 Weakly Supervised Role Identification in Teamwork Interactions ACL 2015 Incorporating Word Correlation Knowledge into Topic Modeling NAACL 2015