Yulia Tsvetkov

When One LLM Drools, Multi-LLM Collaboration Rules ACL 2026 Among Us: Measuring and Mitigating Malicious Contributions in Model Collaboration Systems ACL 2026 Guardrails and Security for LLMs: Safe, Secure and Controllable Steering of LLM Applications ACL 2025 ALPACA AGAINST VICUNA: Using LLMs to Uncover Memorization of LLMs NAACL 2025 ComPO: Community Preferences for Language Model Personalization NAACL 2025 Position: Political Neutrality in AI Is Impossible — But Here Is How to Approximate It ICML 2025 Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence ICML 2025 Varying Shades of Wrong: Aligning LLMs with Wrong Answers Only ICLR 2025 Explore Theory of Mind: program-guided adversarial data generation for theory of mind reasoning ICLR 2025 FACTS&EVIDENCE: An Interactive Tool for Transparent Fine-Grained Factual Verification of Machine-Generated Text NAACL 2025 Biased LLMs can Influence Political Decision-Making ACL 2025 CulturalBench: A Robust, Diverse and Challenging Benchmark for Measuring LMs’ Cultural Knowledge Through Human-AI Red-Teaming ACL 2025 Trusting Your Evidence: Hallucinate Less with Context-aware Decoding NAACL 2024 Extracting Lexical Features from Dialects via Interpretable Dialect Classifiers NAACL 2024 David helps Goliath: Inference-Time Collaboration Between Small Specialized and Large General Diffusion LMs NAACL 2024 SemStamp: A Semantic Watermark with Paraphrastic Robustness for Text Generation NAACL 2024 P3Sum: Preserving Author’s Perspective in News Summarization with Diffusion Language Models NAACL 2024 BUFFET: Benchmarking Large Language Models for Few-shot Cross-lingual Transfer NAACL 2024 DIALECTBENCH: An NLP Benchmark for Dialects, Varieties, and Closely-Related Languages ACL 2024 Don’t Hallucinate, Abstain: Identifying LLM Knowledge Gaps via Multi-LLM Collaboration ACL 2024 Knowledge Crosswords: Geometric Knowledge Reasoning with Large Language Models ACL 2024 DELL: Generating Reactions and Explanations for LLM-Based Misinformation Detection ACL 2024 Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory ICLR 2024 MediQ: Question-Asking LLMs and a Benchmark for Reliable Interactive Clinical Reasoning NIPS 2024 MAGNET: Improving the Multilingual Fairness of Language Models with Adaptive Gradient-Based Tokenization NIPS 2024 The Art of Saying No: Contextual Noncompliance in Language Models NIPS 2024 MatFormer: Nested Transformer for Elastic Inference NIPS 2024 Gen-Z: Generative Zero-Shot Text Classification with Contextualized Label Descriptions ICLR 2024 Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting ICLR 2024 Knowledge Card: Filling LLMs' Knowledge Gaps with Plug-in Specialized Language Models ICLR 2024 ValueScope: Unveiling Implicit Norms and Values via Return Potential Model of Social Interactions EMNLP 2024 Can LLM Graph Reasoning Generalize beyond Pattern Memorization? EMNLP 2024 Locating Information Gaps and Narrative Inconsistencies Across Languages: A Case Study of LGBT People Portrayals on Wikipedia EMNLP 2024 Voices Unheard: NLP Resources and Models for Yorùbá Regional Dialects EMNLP 2024 Modular Pluralism: Pluralistic Alignment via Multi-LLM Collaboration EMNLP 2024 Stumbling Blocks: Stress Testing the Robustness of Machine-Generated Text Detectors Under Attacks ACL 2024 What Does the Bot Say? Opportunities and Risks of Large Language Models in Social Media Bot Detection ACL 2024 Teaching LLMs to Abstain across Languages via Multilingual Feedback EMNLP 2024 LatticeGen: Hiding Generated Text in a Lattice for Privacy-Aware Large Language Model Generation on Cloud NAACL 2024 Unsupervised Keyphrase Extraction via Interpretable Neural Networks EACL 2023 Can Language Models Solve Graph Problems in Natural Language? NIPS 2023 KALM: Knowledge-Aware Integration of Local, Document, and Global Contexts for Long Document Understanding ACL 2023 SSD-LM: Semi-autoregressive Simplex-based Diffusion Language Model for Text Generation and Modular Control ACL 2023 From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Models ACL 2023 On the Blind Spots of Model-Based Evaluation Metrics for Text Generation ACL 2023 Understanding In-Context Learning via Supportive Pretraining Data ACL 2023 Minding Language Models’ (Lack of) Theory of Mind: A Plug-and-Play Multi-Character Belief Tracker ACL 2023 LEXPLAIN: Improving Model Explanations via Lexicon Supervision ACL 2023 Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Survey EACL 2023 Understanding Ethics in NLP Authoring and Reviewing EACL 2023 FactKB: Generalizable Factuality Evaluation using Language Models Enhanced with Factual Knowledge EMNLP 2023 Do All Languages Cost the Same? Tokenization in the Era of Commercial Language Models EMNLP 2023 GlobalBench: A Benchmark for Global Progress in Natural Language Processing EMNLP 2023 Mitigating Societal Harms in Large Language Models EMNLP 2023 On the Zero-Shot Generalization of Machine-Generated Text Detectors EMNLP 2023 TalkUp: Paving the Way for Understanding Empowering Language EMNLP 2023 Toward Human Readable Prompt Tuning: Kubrick’s The Shining is a good movie, and a good prompt too? EMNLP 2023 BotPercent: Estimating Bot Populations in Twitter Communities EMNLP 2023 Gendered Mental Health Stigma in Masked Language Models EMNLP 2022 Gradient-based Constrained Sampling from Language Models EMNLP 2022 Referee: Reference-Free Sentence Summarization with Sharper Controllability through Symbolic Knowledge Distillation EMNLP 2022 Correcting Diverse Factual Errors in Abstractive Summarization via Post-Editing and Language Model Infilling EMNLP 2022 Challenges and Opportunities in Information Manipulation Detection: An Examination of Wartime Russian Media EMNLP 2022 SimVLM: Simple Visual Language Model Pretraining with Weak Supervision ICLR 2022 Speaker Information Can Guide Models to Better Inductive Biases: A Case Study On Predicting Code-Switching ACL 2022 Threat Scenarios and Best Practices to Detect Neural Fake News COLING 2022 Improving the Diversity of Unsupervised Paraphrasing with Embedding Outputs EMNLP 2021 Simple and Efficient ways to Improve REALM EMNLP 2021 Understanding Factuality in Abstractive Summarization with FRANK: A Benchmark for Factuality Metrics NAACL 2021 Controlling Dialogue Generation with Semantic Exemplars NAACL 2021 Synthesizing Adversarial Negative Responses for Robust Response Ranking and Evaluation IJCNLP 2021 Machine Translation into Low-resource Language Varieties IJCNLP 2021 A Survey of Race, Racism, and Anti-Racism in NLP IJCNLP 2021 SELFEXPLAIN: A Self-Explaining Architecture for Neural Text Classifiers EMNLP 2021 A Survey of Race, Racism, and Anti-Racism in NLP ACL 2021 Machine Translation into Low-resource Language Varieties ACL 2021 Controlled Text Generation as Continuous Optimization with Multiple Constraints NIPS 2021 StructSum: Summarization via Structured Representations EACL 2021 Synthesizing Adversarial Negative Responses for Robust Response Ranking and Evaluation ACL 2021 Cross-Cultural Similarity Features for Cross-Lingual Transfer Learning of Pragmatically Motivated Tasks EACL 2021 Evaluating the Morphosyntactic Well-formedness of Generated Texts EMNLP 2021 Efficient Test Time Adapter Ensembling for Low-resource Language Varieties EMNLP 2021 DialoGraph: Incorporating Interpretable Strategy-Graph Networks into Negotiation Dialogues ICLR 2021 Gradient Vaccine: Investigating and Improving Multi-task Optimization in Massively Multilingual Models ICLR 2021 Detecting Community Sensitive Norm Violations in Online Conversations EMNLP 2021 Influence Tuning: Demoting Spurious Correlations via Instance Attribution and Instance-Driven Updates EMNLP 2021 Improving Span Representation for Domain-adapted Coreference Resolution EMNLP 2021 Unsupervised Discovery of Implicit Gender Bias EMNLP 2020 On Negative Interference in Multilingual Models: Findings and A Meta-Learning Treatment EMNLP 2020 Automatic Extraction of Rules Governing Morphological Agreement EMNLP 2020 Fortifying Toxic Speech Detectors Against Veiled Toxicity EMNLP 2020 Understanding Linguistic Accommodation in Code-Switched Human-Machine Dialogues EMNLP 2020 LTIatCMU at SemEval-2020 Task 11: Incorporating Multi-Level Features for Multi-Granular Propaganda Span Identification SEMEVAL 2020 Understanding Linguistic Accommodation in Code-Switched Human-Machine Dialogues CONLL 2020 Augmenting Non-Collaborative Dialog Systems with Explicit Semantic and Strategic Dialog History ICLR 2020 LTIatCMU at SemEval-2020 Task 11: Incorporating Multi-Level Features for Multi-Granular Propaganda Span Identification COLING 2020 Demoting Racial Bias in Hate Speech Detection ACL 2020 A Deep Reinforced Model for Zero-Shot Cross-Lingual Summarization with Bilingual Semantic Similarity Rewards ACL 2020 Balancing Training for Multilingual Neural Machine Translation ACL 2020 Explaining Black Box Predictions and Unveiling Data Artifacts through Influence Functions ACL 2020 Black is to Criminal as Caucasian is to Police: Detecting and Removing Multiclass Bias in Word Embeddings NAACL 2019 Von Mises-Fisher Loss for Training Sequence to Sequence Models with Continuous Outputs ICLR 2019 Finding Microaggressions in the Wild: A Case for Locating Elusive Phenomena in Social Media Posts EMNLP 2019 Entity-Centric Contextual Affective Analysis ACL 2019 Measuring Bias in Contextualized Word Representations ACL 2019 Finding Microaggressions in the Wild: A Case for Locating Elusive Phenomena in Social Media Posts IJCNLP 2019 Topics to Avoid: Demoting Latent Confounds in Text Classification IJCNLP 2019 Learning to Generate Word- and Phrase-Embeddings for Efficient Phrase-Based Neural Machine Translation EMNLP 2019 A Margin-based Loss with Synthetic Negative Samples for Continuous-output Machine Translation EMNLP 2019 Topics to Avoid: Demoting Latent Confounds in Text Classification EMNLP 2019 CMU-01 at the SIGMORPHON 2019 Shared Task on Crosslinguality and Context in Morphology ACL 2019 Framing and Agenda-setting in Russian News: a Computational Analysis of Intricate Political Strategies EMNLP 2018 Socially Responsible NLP NAACL 2018 Proceedings of the Second Workshop on Subword/Character LEvel Models NAACL 2018 Style Transfer Through Back-Translation ACL 2018 Incorporating Dialectal Variability for Socially Equitable Language Identification ACL 2017 Polyglot Neural Language Models: A Case Study in Cross-Lingual Phonetic Representation Learning NAACL 2016 Learning the Curriculum with Bayesian Optimization for Task-Specific Word Representation Learning ACL 2016 Morphological Inflection Generation Using Character Sequence to Sequence Learning NAACL 2016 Lexicon Stratification for Translating Out-of-Vocabulary Words IJCNLP 2015 Sparse Overcomplete Word Vector Representations IJCNLP 2015 Sparse Overcomplete Word Vector Representations ACL 2015 Not All Contexts Are Created Equal: Better Word Representations with Variable Attention EMNLP 2015 Evaluation of Word Vector Representations by Subspace Alignment EMNLP 2015 Constraint-Based Models of Lexical Borrowing NAACL 2015 Lexicon Stratification for Translating Out-of-Vocabulary Words ACL 2015 Augmenting Translation Models with Simulated Acoustic Confusions for Improved Spoken Language Translation EACL 2014 Automatic Classification of Communicative Functions of Definiteness COLING 2014 Metaphor Detection with Cross-Lingual Model Transfer ACL 2014 Identification of Multi-word Expressions by Combining Multiple Linguistic Information Sources EMNLP 2011 Extraction of Multi-word Expressions from Small Parallel Corpora COLING 2010