Lyle Ungar

Knowing When Not to Answer: Lightweight KB-Aligned OOD Detection for Safe RAG ACL 2026 LaTeX2Layout: High-Fidelity, Scalable Document Layout Annotation Pipeline for Layout Detection AAAI 2026 The Illusion of Empathy: How AI Chatbots Shape Conversation Perception AAAI 2025 Cross-Cultural Differences in Mental Health Expressions on Social Media NAACL 2025 Language-based Valence and Arousal Expressions between the United States and China: a Cross-Cultural Examination NAACL 2025 Social Norms in Cinema: A Cross-Cultural Analysis of Shame, Pride and Prejudice NAACL 2025 Systematic Evaluation of Auto-Encoding and Large Language Model Representations for Capturing Author States and Traits ACL 2025 Towards Style Alignment in Cross-Cultural Translation ACL 2025 ControlText: Unlocking Controllable Fonts in Multilingual Text Rendering without Font Annotations EMNLP 2025 Culturally-Aware Conversations: A Framework & Benchmark for LLMs EMNLP 2025 The Impact of Language Mixing on Bilingual LLM Reasoning EMNLP 2025 Modeling Human Subjectivity in LLMs Using Explicit and Implicit Human Factors in Personas EMNLP 2024 Building Knowledge-Guided Lexica to Model Cultural Variation NAACL 2024 Using Daily Language to Understand Drinking: Multi-Level Longitudinal Differential Language Analysis EACL 2024 AWARE-TEXT: An Android Package for Mobile Phone Based Text Collection and On-Device Processing EMNLP 2023 StyLEx: Explaining Style Using Human Lexical Annotations EACL 2023 Multilingual Language Models are not Multicultural: A Case Study in Emotion ACL 2023 Automatic Reflection Generation for Peer-to-Peer Counseling EMNLP 2023 Conditioning on Dialog Acts improves Empathy Style Transfer EMNLP 2023 An Integrative Survey on Mental Health Conversational Agents to Bridge Computer Science and Medical Perspectives EMNLP 2023 Conceptor-Aided Debiasing of Large Language Models EMNLP 2023 Comparing Styles across Languages EMNLP 2023 Interactive Concept Learning for Uncovering Latent Themes in Large Text Collections ACL 2023 Measuring the Language of Self-Disclosure across Corpora ACL 2022 Data-driven exclusion criteria for instrumental variable studies CLEAR 2022 Interactively Uncovering Latent Arguments in Social Media Platforms: A Case Study on the Covid-19 Vaccine Debate EMNLP 2022 A Holistic Framework for Analyzing the COVID-19 Vaccine Debate NAACL 2022 Nonsuicidal Self-Injury and Substance Use Disorders: A Shared Language of Addiction NAACL 2022 Inducing Generalizable and Interpretable Lexica EMNLP 2022 Characterizing Social Spambots by their Human Traits IJCNLP 2021 Characterizing Social Spambots by their Human Traits ACL 2021 Does BERT Learn as Humans Perceive? Understanding Linguistic Styles through Lexica EMNLP 2021 WikiTalkEdit: A Dataset for modeling Editors’ behaviors on Wikipedia NAACL 2021 Item Response Theory for Efficient Human Evaluation of Chatbots EMNLP 2020 Learning Emotion from 100 Observations: Unexpected Robustness of Deep Learning under Strong Data Limitations COLING 2020 Detecting Emerging Symptoms of COVID-19 using Context-based Twitter Embeddings EMNLP 2020 Predicting Responses to Psychological Questionnaires from Participants’ Social Media Posts and Question Text Embeddings EMNLP 2020 Toward Micro-Dialect Identification in Diaglossic and Code-Switched Environments EMNLP 2020 Continual Learning for Sentence Representations Using Conceptors NAACL 2019 Unsupervised Post-Processing of Word Vectors via Conceptor Negation AAAI 2019 Conceptor Debiasing of Word Representations Evaluated on WEAT ACL 2019 The Role of Protected Class Word Lists in Bias Identification of Contextualized Word Representations ACL 2019 ChatEval: A Tool for Chatbot Evaluation NAACL 2019 User-Level Race and Ethnicity Predictors from Twitter Text COLING 2018 Diachronic degradation of language models: Insights from social media ACL 2018 Enabling Deep Learning of Emotion With First-Person Seed Expressions NAACL 2018 Identifying Locus of Control in Social Media Language EMNLP 2018 The Remarkable Benefit of User-Level Aggregation for Lexical-based Population-Level Predictions EMNLP 2018 Modeling Empathy and Distress in Reaction to News Stories EMNLP 2018 Current and Future Psychological Health Prediction using Language and Socio-Demographics of Children for the CLPysch 2018 Shared Task NAACL 2018 Unsupervised Morphology Learning with Statistical Paradigms COLING 2018 EmoNet: Fine-Grained Emotion Detection with Gated Recurrent Neural Networks ACL 2017 Controlling Human Perception of Basic User Traits EMNLP 2017 Assessing Objective Recommendation Quality through Political Forecasting EMNLP 2017 DLATK: Differential Language Analysis ToolKit EMNLP 2017 Recognizing Counterfactual Thinking in Social Media Texts ACL 2017 On the Distribution of Lexical Features at Multiple Levels of Analysis ACL 2017 Domain Adaptation from User-level Facebook Models to County-level Twitter Predictions IJCNLP 2017 Semantic Word Clusters Using Signed Spectral Clustering ACL 2017 Beyond Binary Labels: Political Ideology Prediction of Twitter Users ACL 2017 Predicting Emotional Word Ratings using Distributional Representations and Signed Clustering EACL 2017 Exploring Stylistic Variation with Age and Income on Twitter ACL 2016 Does ‘well-being’ translate on Twitter? EMNLP 2016 Analyzing Biases in Human Perception of User Age and Gender from Text ACL 2016 Using Syntactic and Semantic Context to Explore Psychodemographic Differences in Self-reference EMNLP 2016 Crowdsourcing for NLP NAACL 2015 Extracting Human Temporal Orientation from Facebook Language NAACL 2015 Developing Age and Gender Predictive Lexica over Social Media EMNLP 2014 Spectral Learning of Latent-Variable PCFGs: Algorithms and Sample Complexity JMLR 2014 New Subsampling Algorithms for Fast Least Squares Regression NIPS 2013 Experiments with Spectral Learning of Latent-Variable PCFGs NAACL 2013 Spectral Learning Algorithms for Natural Language Processing NAACL 2013 Faster Ridge Regression via the Subsampled Randomized Hadamard Transform NIPS 2013 Spectral Learning of Latent-Variable PCFGs ACL 2012 New Insights from Coarse Word Sense Disambiguation in the Crowd COLING 2012 Spectral Dependency Parsing with Latent Variables CONLL 2012 Penn: Using Word Similarities to better Estimate Sentence Similarity SEMEVAL 2012 Spectral Dependency Parsing with Latent Variables EMNLP 2012 Improving Supervised Sense Disambiguation with Web-Scale Selectors COLING 2012 A New Approach to Lexical Disambiguation of Arabic Text EMNLP 2010 Feature Selection using Multiple Streams AISTATS 2010 An Empirical Study of the Behavior of Active Learning for Word Sense Disambiguation NAACL 2006